https://benchmarkregistry.org/https://benchmarkregistry.org/modelshttps://benchmarkregistry.org/benchmarkshttps://benchmarkregistry.org/companieshttps://benchmarkregistry.org/benchmarks/ai2dhttps://benchmarkregistry.org/benchmarks/ai2d/testhttps://benchmarkregistry.org/benchmarks/ai2d/test?view=history&result=388329803e62872d8e698ab6c54d71ea67eca5049c385f656ab4e212605d6181https://benchmarkregistry.org/benchmarks/ai2d/test?view=history&result=752ffc72dd601b5c765d0611416f806e853e1a462145837b468a3e1b53bf7143https://benchmarkregistry.org/benchmarks/apex-agentshttps://benchmarkregistry.org/benchmarks/apex-agents/originalhttps://benchmarkregistry.org/benchmarks/apex-agents/original?view=history&result=b30fea475aa14b4ca7b874a36337b3b29c06a54d3354f6150e39593e04b256achttps://benchmarkregistry.org/benchmarks/arena-texthttps://benchmarkregistry.org/benchmarks/arena-text/text-overall-2026-09-13https://benchmarkregistry.org/benchmarks/arena-text/text-overall-2026-09-13?view=history&result=1e701c13ea18657772966213c84ff7b2df40cbf4cf6d7764ad9fadbc20b1c1b4https://benchmarkregistry.org/benchmarks/automationbenchhttps://benchmarkregistry.org/benchmarks/automationbench/1-0-6https://benchmarkregistry.org/benchmarks/automationbench/1-0-6?view=history&result=0203103cabe2f6a8c719f94d2ccf7dcfc4d071af5032b6916d65abe9632600aehttps://benchmarkregistry.org/benchmarks/automationbench/1-0-6?view=history&result=4b14afd90fb1cc979b76f2f3a99a5f1e5610e93a84bd6f19559467343de5481bhttps://benchmarkregistry.org/benchmarks/automationbench/1-0-6?view=history&result=68cdd2ee3907e4cb3e92a62be99220806a076e16c2871fc6a6e6b890f410f124https://benchmarkregistry.org/benchmarks/automationbench/1-0-6?view=history&result=bf480492726b30ca476af03f7662cce24790f5a9a490702bb99ce3cf8048826bhttps://benchmarkregistry.org/benchmarks/automationbench/1-0-6?view=history&result=ecc4e5402fc7b1c96f13f9385ee5455d40a870de2d5d66cfac86a21854fd8313https://benchmarkregistry.org/benchmarks/babyvisionhttps://benchmarkregistry.org/benchmarks/babyvision/originalhttps://benchmarkregistry.org/benchmarks/babyvision/original?view=history&result=bc8b8521bdb48c640fe18632419afc127064a3c099baf5f3b011149f5d9ddfe5https://benchmarkregistry.org/benchmarks/benchcadhttps://benchmarkregistry.org/benchmarks/benchcad/vision2code-with-toolshttps://benchmarkregistry.org/benchmarks/benchcad/vision2code-with-tools?view=history&result=0f84c8b9902d3f0a5d911ffb062d4fa70e98b56f9bcad0798cd9171f79fe5822https://benchmarkregistry.org/benchmarks/big-bench-extra-hardhttps://benchmarkregistry.org/benchmarks/big-bench-extra-hard/original-micro-averagehttps://benchmarkregistry.org/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=35e16878fd44f78f8307a611b4a1f77476e8843887b9acc7d1c87ea9bd3ad645https://benchmarkregistry.org/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=72e08f914521ee1aa4e5f6fdbe57b86ae56177361b8c302e74026e7bb77a690ehttps://benchmarkregistry.org/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=a03e35322783f9ed3ecdb5781501f8f9ec19e0644fb16a2b558c9130c582274bhttps://benchmarkregistry.org/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=d2b97589860071506457aaa315c61b73d2780b8a67fac55c3371a0eb310d909dhttps://benchmarkregistry.org/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=f97f0abb847cd01ce9a688196c5c1a42062dfea42208a8b4a9b9c833b77c6532https://benchmarkregistry.org/benchmarks/browsecomphttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomphttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=1bb9d032826aa775ee6e7cb8320a317b441014895e459194be19f30509b88a94https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=2c7b8e4b6b77ae21a60c9b8be3180cfc98b8744a96f862aa089204f1dbafa740https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=6349581e5394b4d07ba61aee433e71f08b55eee1457cee0227dee6ce73c80d3dhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=6354698365a1f1185fdb015e52c65d72575fc5f8d47934eab6d132ef79c0bf9dhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=6f5ab45aa43a204281799ac0023582ffe16915713d8b42e781654afe742b175fhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=70e9711cd171e3116a645a50fc590fa7f01aa35c80493987eae745765450a16ahttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=80ace69677b9ab7d311af0fe374c0790cc6912e5d7e40d82c479750b6b801231https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=811fb18d7d6d1488db8d3bacc65ee2da0fe9726f934dc324dfe13a5165f34a07https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=81674dc0d61a33770688302c89835eefd8e7fe5affb8a0c590af4db0a88fb434https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=8b04c9c8430d592a828bd44ae18e83dc11772349647055300aa794b0f438b3bfhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=9fb788b8938318f874b1d7a8f730cfda5fbd48c75bbdb1cbd9a704cc105ec8f3https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=bd25dda2569858cbe603470926a6b7d258f346e7509d125a1bab5a93b7802f7fhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=bd80caee652790cd23d4a537390e4932575bcf9c74977356af975d2700c012c0https://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=c0b0cc414a8eba2e3095e78f9b23dd3da747b9f34848a40f0b2b35e87ae57acdhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=e20186b67f444da8cf3a669de85cca6f445f87481c85772f2911e7a8dab2679ahttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=fc0c0ff4c1803d469e7747368c9085450ff92e5000f169d1f0acf1d0fee789edhttps://benchmarkregistry.org/benchmarks/browsecomp/browsecomp?view=history&result=fc746279eab8455f0fd07ef4e1131711cb5db668bf00b0623a7d95e07ebe97f9https://benchmarkregistry.org/benchmarks/browsecomp/context-management-minimax-m25https://benchmarkregistry.org/benchmarks/browsecomp/context-management-minimax-m25?view=history&result=22b646d1ef8a6d7769e437cd0d9ca13a14ba867c557ee38e95f99df2c289a57ahttps://benchmarkregistry.org/benchmarks/browsecomp/with-context-management-inklinghttps://benchmarkregistry.org/benchmarks/browsecomp/with-context-management-inkling?view=history&result=697ffb71136d7a7b29ba682f99878ef58ff3160e8d2c284bbe19d5b79c311cd0https://benchmarkregistry.org/benchmarks/browsecomp/with-context-management-inkling?view=history&result=9c133a69cc2e5a1ac8b61a84efad1841f18bdd8d303260638a25cfb8ae949100https://benchmarkregistry.org/benchmarks/chartqahttps://benchmarkregistry.org/benchmarks/chartqa/testhttps://benchmarkregistry.org/benchmarks/chartqa/test?view=history&result=a9e62c31553526dc24d20bbee6e97be3de6af2173037ddd86363fa0b3281325ehttps://benchmarkregistry.org/benchmarks/charxivhttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-toolshttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=003e781bc072fff02d3018a1e9218f5957bf2cb9e7279b48279327aaf10181f3https://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=093c363f056bb70b902ce74d5ecf74dac41b2330f6a678f0d516eb1367ae40abhttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=1b4d96e71ab0349d46f86692ba83b728235efd27429edb8e5c5be44988d6456chttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=1ddf3b3e1918b72f6c7c1daa3507bad7d6c651896b7da2ffad2a84dfd849ed02https://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=5c94f09584499568c0c3203ee66b6c26df28f35d539cac355f309e5010091a8fhttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=6ea0e6813fbbc3220992b8408ce62f0b2f84907e0dc970f8886224bf1cd1087dhttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=81dc68dcc2888c887e360b0197594dbfc2579e134bd1b4d417350df16e1291f7https://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=bcbfd8484dd723c89b3cfbb7963d40b314d406a28eb79e514d970bcbd15081f8https://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=d5592c5cb37ba3380ea9e10f2517be4349f907ae508d4acdfad412168b180e67https://benchmarkregistry.org/benchmarks/charxiv/reasoning-no-tools?view=history&result=eed903976ffe0073ab8c583d274207bc5dae18f5b0366f92a27c5127057d2a00https://benchmarkregistry.org/benchmarks/charxiv/reasoning-python-enabledhttps://benchmarkregistry.org/benchmarks/charxiv/reasoning-python-enabled?view=history&result=71fbd29832b1e603777e6d60d17784397f39912521cd9f2a2f1a119cc57eef4dhttps://benchmarkregistry.org/benchmarks/codeforceshttps://benchmarkregistry.org/benchmarks/codeforces/no-toolshttps://benchmarkregistry.org/benchmarks/codeforces/with-toolshttps://benchmarkregistry.org/benchmarks/cursorbenchhttps://benchmarkregistry.org/benchmarks/cursorbench/3.0https://benchmarkregistry.org/benchmarks/cursorbench/3.0?view=history&result=092ffebb8d27ecff84e5d8181d7eac44ed5e9ca6bfd5daf5cf38ddeb35587348https://benchmarkregistry.org/benchmarks/cursorbench/3.0?view=history&result=41d72aecb1d78318b9652ceb09c04dbd5ea5bbe914904dea9fc2dd7e4d301a8ahttps://benchmarkregistry.org/benchmarks/cursorbench/3.0?view=history&result=cebc672dd52863198dd99ee2e38627df5d04f75f52e419cabd9621a5adfdbc80https://benchmarkregistry.org/benchmarks/cursorbench/3.1https://benchmarkregistry.org/benchmarks/cursorbench/3.1?view=history&result=8a86f945cb5cc577227287ef1dbf610709bd404d0ecf8e42c2efff293a1db1c3https://benchmarkregistry.org/benchmarks/cursorbench/3.2.0https://benchmarkregistry.org/benchmarks/cursorbench/3.2.0?view=history&result=3ba369f2a37e42785bcf865c48e1200c2b40e287f1cd39d588a22d0e602df2cbhttps://benchmarkregistry.org/benchmarks/cursorbench/3.2.0?view=history&result=88a7c50a9ba66d2d7afd0763085777d7490c52d44725c6c70f0ca76879cff687https://benchmarkregistry.org/benchmarks/cursorbench/4-0https://benchmarkregistry.org/benchmarks/cursorbench/4-0?view=history&result=0e213b1889c14530bb4966ec7d13f2cc3c7a36d31924f69a7debd443f2c8ee6fhttps://benchmarkregistry.org/benchmarks/cursorbench/4-0?view=history&result=385f9f372337a93943da043ef98ce4c98ca5cdefeb51ac4567cf4fcd5495b3e1https://benchmarkregistry.org/benchmarks/cursorbench/4-0?view=history&result=3d96bacf7019860079b1f414d498696e7fcbadc2bc12aa9509b8d086c593f1d3https://benchmarkregistry.org/benchmarks/cursorbench/4-0?view=history&result=5b240f64f9c3427298fe24d938af541bf83215bfcc72d578f3276d77c48c9e7chttps://benchmarkregistry.org/benchmarks/cursorbench/4-0?view=history&result=b19cc99f8581a76a68e66516fdb16618bd1d1d3352a643ba868371b86f0faff4https://benchmarkregistry.org/benchmarks/cursorbench/4-0?view=history&result=fe6f5d5b7af3c48e5b3a051be8cf2ec27b9b93b741b5e0a29cc393c5d850fc0ehttps://benchmarkregistry.org/benchmarks/cybergymhttps://benchmarkregistry.org/benchmarks/cybergym/originalhttps://benchmarkregistry.org/benchmarks/cybergym/original?view=history&result=01e65d639d77332018d51ea4e671718faa1acb93fd76e3009cb8ae9575ec7b5chttps://benchmarkregistry.org/benchmarks/cybergym/original?view=history&result=1421534eabb88eb1fe44dd205a73e950f0e38165700f7e4f05782b422ec74834https://benchmarkregistry.org/benchmarks/cybergym/original?view=history&result=397adc10a5bb4ff06fef438b553c98fcedafddbb4f13c06a0a37d304baad8cbbhttps://benchmarkregistry.org/benchmarks/cybergym/original?view=history&result=666ff8d02384b7a144cd194b8a9b355fdb7d91244946621e8f10a7b4f2ef43ddhttps://benchmarkregistry.org/benchmarks/cybergym/original?view=history&result=cd7c2b4f4223e43b164eafe5f35fc8faa47727fb9d3c859848bab33faf5547b6https://benchmarkregistry.org/benchmarks/cybergym/original?view=history&result=db45a9437b85cdba841fc9e89741c89b26abd9853ae4096114711d06787844e0https://benchmarkregistry.org/benchmarks/deep-swehttps://benchmarkregistry.org/benchmarks/deep-swe/1.1https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agenthttps://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history&result=2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history&result=80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3https://benchmarkregistry.org/benchmarks/deep-swe/1.1-muse-codehttps://benchmarkregistry.org/benchmarks/deep-swe/1.1-muse-code?view=history&result=5ef68d4fb3a741d1fee48a655ae74c602c60b5334fbdf34bcbeecd027f934a32https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=00345482e38f5491404406972f9b54afe1effbe1d87e7850fe9e65aa26940782https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=00ef6704f1169a68d6b2f04768dd05e44c3b820e63ddde70ab67372718ec7b01https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=08ad750b46f6afc1ab42e3e9fa240d38cebad8688364bb2f19187f5f9f51cca9https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=10eb344a4b609fd1ffa521d2e4398a7b76fcf8be89efb0db92cb966ed667e219https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=1286b2e0b2ee33e4258a0c9faacc3c3251a231ca109afd0d3b00b3ee07af6106https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=1c63991153518a478eb1f18f4bf12e20818d2199a3b73e7ebcb8fcb687fcba50https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=21a523440fc8bd3c3fba546e741f31b5e47158f59ea4e68f909170b07e692f9chttps://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=3038ca6ff670a26758cf55c19be9a7877b6993a57f8dbf007432669eefd63299https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=3199d683ad756cd30fe401d1a8cc8f724920b7b651ebdef346e864102df3e34fhttps://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=3be3d3420441e722c6c0e1a42d2e3a2a9c204d4baaa9fab2bd893efbefe8a20fhttps://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=42fe0f16a2536a4a47b21310bf2fdbba1ccdab90ad7806818555e9d53b5b8e3dhttps://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=47c119f902f60b66451677acf1c44b609bf1ce23037a65bfba022cf3527db2cbhttps://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=486340afa38a52d5403554fa8ed2f5d1bb6b0938b1cd908493273c9748961a2dhttps://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=64b8006ee7087a593679afbad34377d2dc140db970c7b2cc3826f1a7e452dc11https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=76109f8250c0d324e17c896040ecd17f34f1383e9dbcb929b5eb7d4c653b7979https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=a83a860812d7843d995937d86e43cb71c14ef695a03e538d5c16e00b5522dbe2https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=ad0a311db1377b7dcc9a981816e9c4291ca257b64bdd786a48e294782b1a8288https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=d9489d91e78e24bb1bcc46529bde655d698a578b64f38be7e7a866aa03da7407https://benchmarkregistry.org/benchmarks/deep-swe/1.1?view=history&result=f43a5c95bb026979c6536eaac96c114b86d3f3b26d3b326543027272526b3e48https://benchmarkregistry.org/benchmarks/deepsearchqahttps://benchmarkregistry.org/benchmarks/deepsearchqa/900-prompthttps://benchmarkregistry.org/benchmarks/deepsearchqa/900-prompt?view=history&result=1d08a4765901ce94a392ad7b99261434bd82cee4627cee909535ef4250b7e56dhttps://benchmarkregistry.org/benchmarks/deepsearchqa/900-prompt?view=history&result=b8af3781860d58b5ee17900ead2002184890145314e6229e66d3abd8b6315abchttps://benchmarkregistry.org/benchmarks/deepsearchqa/900-prompt?view=history&result=bd94e2c27815c8a5b4e6b36dee26d1dc1c9a56bfe499f818c5639ceeedeea35ehttps://benchmarkregistry.org/benchmarks/gaia2https://benchmarkregistry.org/benchmarks/gaia2/public-800-taskshttps://benchmarkregistry.org/benchmarks/gaia2/public-800-tasks?view=history&result=4321095fbd62bf0e977d63ace711d353afac6b2fd5f68a1f5a39d37d8ddfad63https://benchmarkregistry.org/benchmarks/gdp-pdfhttps://benchmarkregistry.org/benchmarks/gdp-pdf/gdp.pdfhttps://benchmarkregistry.org/benchmarks/gdp-pdf/gdp.pdf?view=history&result=12c4a1329c7a37dbcc9c1ac334de8dd8f8bc4e1e40dbcbec707f4fd1796a1733https://benchmarkregistry.org/benchmarks/gdp-pdf/gdp.pdf?view=history&result=45b61e06689f572ce72ae2959649c4b3369e3ca608e7f526b7ba0addb12d1377https://benchmarkregistry.org/benchmarks/gdp-pdf/gdp.pdf?view=history&result=723b4a8291aa7647c855ab92f2ea71a79227643997694c38df135bd72aa1fbechttps://benchmarkregistry.org/benchmarks/gdp-pdf/gdp.pdf?view=history&result=baf97fafa08a77128ae48a26b74ff9762eedd50947a49f7c1b6aedece140a4c9https://benchmarkregistry.org/benchmarks/gdp-pdf/gdp.pdf?view=history&result=df9370d941ba4614abc27f775b4ad02166c1c7b4236fb8c93a1e7869d0d7f770https://benchmarkregistry.org/benchmarks/gdpvalhttps://benchmarkregistry.org/benchmarks/gdpval/gdpvalhttps://benchmarkregistry.org/benchmarks/gdpval/gdpval?view=history&result=39714798ab5b1ebdeef1d015a05f39bb0bcc9f435e0c347b7efc30bb2e4e99dbhttps://benchmarkregistry.org/benchmarks/gdpval/gdpval?view=history&result=99edc3cd7af383e2492b902623b4c8c12415ee36259a6756a11680b788cb578chttps://benchmarkregistry.org/benchmarks/gdpval/gdpval?view=history&result=9afe9a15e659d124381519ec7f4ac71221127f859567a6df7d77b35a3ea1816ahttps://benchmarkregistry.org/benchmarks/gpqahttps://benchmarkregistry.org/benchmarks/gpqa/diamondhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=00e2702ac4474f3ea00f945cfcc0871ce8514ccd1080b33388a107eff0078eechttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=09285ef4d0a794e441caa1c3805ddcc85105a76486b2ba8bc744c0ce476f59cdhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=196b6a72ed7dafa02cde3b61ff1668444799cd43b214a58fcfc5898e80b2db44https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=1ed4e63bea6a5ba88998739c92a623cc209470500c6161889c72d5252ea9ec68https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=24077bbeaef25bc07717c0bc77b94af69e661b606836f8df6c53bbe4a4e90db8https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=2f6a94e9aaaf515744287ad83b7323f923465c62581a715cad9a5b30fcafa346https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=394bb4695b78362ea091299bfc80156ad0852b25f4de54c22e199d511e414045https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=4fd521545a7e47c529356924c7b61f9d2775c574f1859264e4a5091bd2599f13https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=53cf08fa7be999dfa070b245e8149485ef59cb5d33a48dc252e604688c052194https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=58e1c8cc321d5876ac6b327bb77cc69e1ddc93f5f88c3b22522e5f26e8b60080https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=5b46a8bc268ac1e0dceb3bcbe8a15e6580e6a08f4d3dd06d412e4dbfc92f60d4https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=5dd4f4658e1cb1c752270d8fac62b927e7ee2181c1d61f08c1ac0080d7cacc42https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=5fe64629d4ff84a596680d0335cec97f262ae5d7f6bc881e943e6a076ef20554https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=617928bdaa590c28b714173293696589ba1ff491dba7470c76fa7fca5c860988https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=734372ed21dbd9483ba7738c96f6c873a056414acab2cf469d630de2cccd8df8https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=78e3fba70e6cdaf4de42feaac273bc040bed99c98fcf65005a63b7d0c7dbd08ahttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=7f7ee2b62a41f351cb30249d135a51e353cfacb3c88c7ee91d826038eb07afe9https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=8b2429d9402191fd448a5506e5150bd10a6cc99e75d80b3d0bc28ac4c627b6c4https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=8baef06161d2a7cc7ffb2d1f290dd1281f24a56c12f1d235994bc58893f45f76https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=8e528f479b7d8ecd202758a947409404d5e9eaae1a7c5d9dbbed16d693db8a0chttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=91618aa222c96a73a81f9e66b53706e7e3dbbe76b74f9b0197b7dbf8d0936a53https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=916f1859c0dc3a78eba98e328246b34912237b07538f89c93bef92589014bf11https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=92f086f214c8716b7f5bf86b25664d03a01ca53f4b68c7e48d265856b9ef7984https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=9453e5cdc905127ddb72ee92e6de7bf63410765ec00c0399da04696389830b55https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=946d879eb89c9da10ada45985a2a078e493166b4c5fae890ceaa3ea94effad90https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=954e1ccf48bd3505fd975ab010bd795136c7c7efaa93872d0378d23076a185a3https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=a2729abff69dc6f526c04019704e1a230eccf3058c9e551e3b14b0fcff6a5ba2https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=a57dacfbf0416e62ff571a78759e08e2c39b3a39cceb2f08be85183eb1a01731https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=aeac84ad22f4bd670e53b5b416d8681202f7f6d4d307506aa31eeab91c8bc95bhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=aebab58d7f07c27a848b75e8a2bacb86abc37070172d5a3541ae76104c52ebeahttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=b5b0386b709b11feecbf75f65f58aa81dc49049337d81abb7a23bb136fd743afhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=b6f0e59bf18915951de6db690f178837166135770c319746004b4a2fecd2721bhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=b9a38e205935784ebfdfebdd023dd452fbd8f95bef77c7336f8ebac2df1c659chttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=bbbc94cc78d979869d97abf24c3ca11995e44dcff8d1e88e923a373498c5beeehttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=bdaf94d5ab0fa93b36fdc59d0621ab81c652bf56f4ec191383686757d8816b2dhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=c04136ccb1cb6834865c1113dafc9044559577255d1dd62448e451587bab71dehttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=c394cffeee4da9bda04f8e670a70697ba3efe529e99cbd222e99a604dfb84475https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=c4d898e3e476b3e5ab2f8d22ce5ef25b202c73005211081b729d89f90ad7fdcfhttps://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=c9cb1116db24c17d240bdb5f6d715a0ba683e886c1d7cf3b69f969d9c1772e89https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=cdf72405aeb3ae3898ccc28a0e1ac594cbe87bac8c2bd963c047e6335b5eac48https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=df487c023f815491b15cce3a7a45d7fd551a30f7faeed6c877b7ec835c525a30https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=f741d056fedfa35ce0a1057f9ed4f687ec489e2abeadd8bc7098e6973f213ea9https://benchmarkregistry.org/benchmarks/hallusionbenchhttps://benchmarkregistry.org/benchmarks/hallusionbench/originalhttps://benchmarkregistry.org/benchmarks/hallusionbench/original?view=history&result=65d5a4f176f6f5744a6054e24f682f0661411553fce457378195a40580ccd508https://benchmarkregistry.org/benchmarks/hallusionbench/original?view=history&result=72128bcca9b6a6cce602b6d147280c809771a41701f4590ac4d8f3209a61e8b1https://benchmarkregistry.org/benchmarks/healthbenchhttps://benchmarkregistry.org/benchmarks/healthbench/consensushttps://benchmarkregistry.org/benchmarks/healthbench/consensus?view=history&result=729f4d612ceb66667ec7669acbf179ba19598d805f14f73423b750ae81ebb34ehttps://benchmarkregistry.org/benchmarks/healthbench/consensus?view=history&result=b949e220907b72c55679f91c6b87af2b1c619a46202fd4ec74885a50d0379034https://benchmarkregistry.org/benchmarks/healthbench/hardhttps://benchmarkregistry.org/benchmarks/healthbench/hard?view=history&result=b8949a7771d539aa42251f42dddddb5075cc28eb392fa8b7cca1ae3ff5dc6ffehttps://benchmarkregistry.org/benchmarks/healthbench/hard?view=history&result=bcd52a9d46763ba5096051e95550297db07d060517aa3e5530ab6d58c8d68df2https://benchmarkregistry.org/benchmarks/healthbench/healthbenchhttps://benchmarkregistry.org/benchmarks/healthbench/healthbench?view=history&result=41c661728adc6ae8ecc2ea4f79321e9936651c5741d95bf10aa10deb3c25790ahttps://benchmarkregistry.org/benchmarks/healthbench/healthbench?view=history&result=8249e76fc6ded2f14b21daddd5f9e653ea88d067b304f2957b4a5cbb0255187chttps://benchmarkregistry.org/benchmarks/healthbench/healthbench?view=history&result=cead249e76e0fe0dd027fac3d2914570a2c7b4d344158bdb698a910b2df03067https://benchmarkregistry.org/benchmarks/hle-verifiedhttps://benchmarkregistry.org/benchmarks/hle-verified/full-1811-item-sethttps://benchmarkregistry.org/benchmarks/hle-verified/full-1811-item-set?view=history&result=5b6d35497aa60800416f666ea53a5669ca6ab739f7a2d35c00ea14a084e8061fhttps://benchmarkregistry.org/benchmarks/hle-verified/full-1811-item-set?view=history&result=c03438470ab0288c297efa5e4885f6619f8ac5b75dc86e0eeed02319f0807210https://benchmarkregistry.org/benchmarks/humanitys-last-examhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-toolshttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=0b1faec5a6cc5955d52c0ea32446332bd3b7f5bea3eea989b4c853acff6a3cc9https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=3bea7aa31d877421be069966ac2e3f4d661330d8545b619f46fbb56087e2f4d3https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=3f269ec17cd9a078b2552dee867893bac4b9675fbac37b8beb59a48679cc2c9ahttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=42259d306578ead02badb9fb9676309aa375be0505103d65a1abcfd579f7a1c2https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=4f927eb9f931bd12ab76d2728a4f32a748e79c0c2f1878b4dfdb7e2e6eb101c3https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=51928710d37981d90df5a2241f27eb1d4af63173bd45cb5113ae698693dfa128https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=5b86d15d6363b539f4a520bdca5e7dc7db380b26aed202580088057588e0531chttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=722a94fdf7c8eef20cbd7bf2d4bfd8fc1792b3adcf624a1048acde13c1bc4d6ahttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=7ab1f14910f776f78d2c4436774114090381b90be79bee3174b55260d85eea95https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=7e409db089597b0fccabe5cc0c2875ab23f039ba340922400fddb5fb53741a7bhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=8b121c313816737362eba29228de2a4ecde165b8f1ca031f93df4660d4f95947https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=938e1f7e86809cf7879838b27887791900a231646f055c6bf164032a2b1e685ahttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=9399d264e9bb7dbfc36c711e6ec6bb2a4755f465f2e005bc1656c47d77e585c5https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=b4175a3eca1ff696c4c8fde0b1b18b6513b8a0ca6e3bb3ceccefd9eca58e5472https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=b82b71be93822347be8807b7f7a7d76d7a8fe1af43b80da5657990cff3ad5a2ehttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=bfd80511267c5243ff89d5e73906419f0a2086c7c87a4ca6a4e57b2c754b724ehttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=c185b3434356e1591bf8c2347b1376d9e400f09022247643faac4573dece046dhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=eaac103d0a931b731017dc22b273d5c87f5d927e797d3585d8b4ecaa576609a0https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=f0c2a5403152e3e9ed7f7563967482b94e04d3a7a29db60c3e1903c11a81a178https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=f4e19702eebe9c51f0723a212015444d812b511957654b5e8e540a4910a84018https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=f864f64186f26bcd81062e97bd5ecc753fb26612c43dfe746ba942f35eb376b4https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=fcf11dfddfc9bc3d84b667fc8b127217d1bc0f239d582fcb4018359866066a2fhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-no-tools?view=history&result=ff0d86abbea2b4cfadd219234df35e2b4815d7cf070543ffb83735cc2123297ehttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-toolshttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=132c955a3ba2007f1dbb6bcb22ad1ba6fed2c4586985ae8c4c8c525fde6366a4https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=14f5a255f79e0760e2f980ab2924fe94dfa1fc07a260a3840cf05f0479b6c678https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=185e4d92d1bde5e2c7c475822265cfe33e01fd5fa5468b424f618cab5ba45d7dhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=4dac73034abcee49a72b7690ae46b1551a99225bae9064d8efc8e92154a2bfd0https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=583bc60ce35dd383ad9737fa7d84976f8a93c3649d7edd27bef6301963a60ec9https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=6c46889c8df1dbb323e9cd27f9a9ad4976937839d2babdae62170f86f294df6dhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=6dd11a2a1c04c3c4c3ac98e58db76ddd81e9525b2c7d1140e6e615d3e966737fhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=6e1dbc464ea44bb95bce0915d36edd6d24b4ccda4bb4f8cbbd86786dfc729365https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=6f0768e9e72a4e6a275f9ef13b42a616131e0f63d33078fa676ffecc1842e849https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=7bb00a578d87b2e33881a4b3f2cf9f6aca1f970db0d3389f5b363fbe71d3742ehttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=9a40fd47577c3693f57baca7a34847abcd5025d051518d1ed55534dbad338badhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=b1ff4cea8605235de05af59af3f20e106d3c5dd49cfa32272703a8b8a1b31366https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=bbd9198daf7bed4d1dd1c609ae3555349397b73a875583a37d5e7edd392ca342https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=c09a0cbaaa1c941000c409168f0f38e9cc33943e0ddaefcece1cad44e541a0fbhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=dba3b4f0240e86696230e1ac51240c5c497484d277cab74c4f5da3488b87239fhttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=e045bf15ab44dde00b5febc61ee98c922d62ea87c438d023c46513f9a022780ehttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=ec0181a061d2048b79e63e3f6c1ca87e1034b0f61163751bae03a21eeed83cb1https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=ee15491193ff4c0d4d5d596a531c0751c0ba3a55dee282d8cb595d0b217ed9cchttps://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=efcd195531eb3a3a84d08cc82722d960fefaa8bee8d83ad2cf5ac2e3379a9f35https://benchmarkregistry.org/benchmarks/humanitys-last-exam/full-set-with-tools?view=history&result=fe83a0e26404e67012ef901f10daf5ee00fceed3d16cd2774a6923846a4e41d2https://benchmarkregistry.org/benchmarks/humanitys-last-exam/no-tools-gpt-5-2https://benchmarkregistry.org/benchmarks/humanitys-last-exam/search-python-gpt-5-2https://benchmarkregistry.org/benchmarks/humanitys-last-exam/search-python-gpt-5-2?view=history&result=4d0df363f9d33cf9adc54548ae2c6cd9cc3d2a92dc48cb9e680ab4acb52042bahttps://benchmarkregistry.org/benchmarks/ifbenchhttps://benchmarkregistry.org/benchmarks/ifbench/originalhttps://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=0af59d28b745874fb62887e2894fec384eca4401aae7a87eb04cfd92070f6226https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=2941d27f2872f3c679c95c0a491569f3c308c7855a56937c6f63ac473aa24643https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=4ee2deb50843652c9522187111dc812b305304e5e5caf93fc4ee22c7cf86ee68https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=5681aa67f24af3ab90899b7c68f8abe9284680ae6d4661ac533fb4370dd4f902https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=58f06fefe069b13e2dcc4b5ccb62ee7703bc83378726dd4d622c638cced572f9https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=704493e43dc58ffdb7aa99a03741bb5418a6e399d50f11840690f56c07e419e9https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=746c78a3816ba91de55d7b9d91b079a73c862ec7750e157acc82304c5e24e8a0https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=7d6261c5d345672fa6388251a0e0eefe3dad20006a7584aae908c110066eaedbhttps://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=86d1ca185d97057655058c3b24cae7142d2a9a2051c547e9329085686ac1ff59https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=93c495a1834cade79bc05a33cd3854d95a751d18c9d573d8536344cf2eaee629https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=9754ca5c54aad4df65ce145e88c0197f37b10e45e0c5206ac615152ac8a98c65https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=983d67c7b825692a200b098a95328229de9f9d5f99bceafe10df82d247256bc7https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=9907d8e9cf4369671058046d38f936d33ed364f01f51481d6877bbf771704617https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=b4c12ec14070f133d5687dcbfb7f0a26dbbf15292cc98358d4c034cfbd4f8717https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=d3a4145286f1b4911748108759443fd2657a7508a3ec37950bb183a91f2083f4https://benchmarkregistry.org/benchmarks/ifbench/original?view=history&result=f94663a425dfdc9a3140f472d21b87ee6401c6e9b50f1847e049cacd9232b2d4https://benchmarkregistry.org/benchmarks/ifevalhttps://benchmarkregistry.org/benchmarks/ifeval/originalhttps://benchmarkregistry.org/benchmarks/ifeval/original?view=history&result=02a91b7843d0b71dcc87b2e86bf31c6522a4bc81342d390b45bb713a1068a2e6https://benchmarkregistry.org/benchmarks/ifeval/original?view=history&result=277fbed9c2b50ff98aaaa49c2c6741ee5ef1838092ab241b7bae6709ae6acd30https://benchmarkregistry.org/benchmarks/ifeval/original?view=history&result=7150fe9a2378dd1b5f7ec0a0654109e23ac4fcfa1ca3328dfe660a199e1a7c74https://benchmarkregistry.org/benchmarks/ifeval/original?view=history&result=8284282d3311d1f9986f050914be465bea65b32387e9b985ec79e4b9a716ecd4https://benchmarkregistry.org/benchmarks/ifeval/original?view=history&result=ea74b8ca3cd0250a308e5a8bfa12a6bd51b3635aa8752e102b5783f9c09cf59bhttps://benchmarkregistry.org/benchmarks/jobbenchhttps://benchmarkregistry.org/benchmarks/jobbench/main-65-taskshttps://benchmarkregistry.org/benchmarks/jobbench/main-65-tasks?view=history&result=10ed1447edd515893f55af18549555e2913a9a3bf2f9c4d8d10d2056a50e573dhttps://benchmarkregistry.org/benchmarks/jobbench/main-65-tasks?view=history&result=3a8cb364c648dce88a3c5661a51ba89398f25e8f3f92a71ac83dd1f2c1d421c5https://benchmarkregistry.org/benchmarks/jobbench/main-65-tasks?view=history&result=8f8fc6592246430218d841ddfeebe863123b91864d1e895c0baa99aee2c99064https://benchmarkregistry.org/benchmarks/lvbenchhttps://benchmarkregistry.org/benchmarks/lvbench/1024-frames-agentichttps://benchmarkregistry.org/benchmarks/lvbench/1024-frames-agentic?view=history&result=f245a6db42ca69727adac89e0f9b38940d4c08911072f8e32d1ca797a531f28ahttps://benchmarkregistry.org/benchmarks/lvbench/1024-frames-statichttps://benchmarkregistry.org/benchmarks/lvbench/1024-frames-static?view=history&result=00484acb308f1e169d68afd7eb4019c5e75b83f0b8313877479b755f975f245ahttps://benchmarkregistry.org/benchmarks/math-visionhttps://benchmarkregistry.org/benchmarks/math-vision/originalhttps://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=326a9070d332143f78eeeebef7e65322bfac9a3454875ef73c3def6f916dfbdchttps://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=3a2a2a00b1593b22d39d79aaf469e4dd713c4907a57f6db08213e02555a9292bhttps://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=54131791114bf14f60a8f7a815547d4673d6f56b2bffaa5cd732f49bd9e0b341https://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=5722e842aa9a82efcde0916aec0a5814d2b155ac1a329cf70b6482f8759dbfeahttps://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=62f39bc2a0c7516086ddc6848844d914f00980c90a61cb4c3c613ff4edec5c9ehttps://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=9d79d71fa33df478b717553931bf21b840fe5c167fdc413aa8b2648fa861c2a0https://benchmarkregistry.org/benchmarks/math-vision/original?view=history&result=a8a88f7c5d4dc88d3c9d595dd1ad85922cd4e4507756965c5d95f8e078bfe9b0https://benchmarkregistry.org/benchmarks/mathversehttps://benchmarkregistry.org/benchmarks/mathverse/minihttps://benchmarkregistry.org/benchmarks/mathverse/mini?view=history&result=2923d442833d9d4ac224db3d671261b745fe011fb2c204aa4b721e4980f83964https://benchmarkregistry.org/benchmarks/mathvistahttps://benchmarkregistry.org/benchmarks/mathvista/minihttps://benchmarkregistry.org/benchmarks/mathvista/mini?view=history&result=dd8095093ee2a9dc2b861cbce2eae666027b36d4301127bbcc999de99d4a718chttps://benchmarkregistry.org/benchmarks/mathvista/mini?view=history&result=f71b7576d481abd41054ce0457c410a43388aa560dbe9d94ab4ad343e4ffdbc4https://benchmarkregistry.org/benchmarks/mcp-atlashttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=040c4a2b8b0f8524f26ed23c4d085170d338839560f7318db6f92534d29bfbf4https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=0d767e922c106e0f12a3310f5bb759fa0d2eefda557de262c26770c0b61e845ahttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=11acbf398644ffbb6313ee3407d4f54c0e68868e5c9dd272784a79f71d850182https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=33a4c35d33eb3513a5091f0612b4706d6f7dcf9090466221b56d94dcee14daa8https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=371996bbc4c8c220a7fae5a477a44bfc63dc01a2dd4b839193d70d0b2ab4875dhttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=3d0580d327105021504da9290e87d5346a61ccf8e51c05dd93d28a7374c5c84ehttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=444a2c85e2fbeada68d02aeec887f9b0419fdabf14f583ccde9fcbc42ef6ed83https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=4456fc2a19f7cc32215db6f4d9178eb32380a6cdb04f32a2ab8be3e4912ed7c0https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=509bd5787987f812de2d680c754d5d71864ced36beee4bffbebcf7a640566bcchttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=53b84c2643a21d3e9cb0424bd0956e6560b6b566b9aa2f48d8dabbdaa50346c2https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=5d96b33cea625d0a6d725d63f4f9d56dde8f076091054a1d03d64b386cf8e507https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=6f47f675a75a9655359827540789c55de4f25f9696c87a32f35758a428a05970https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=6f5855a830828c6d1bcb08a7b27a0b1ff4d4dfdaac0d4fdbdbf6ba06a76d1ad2https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=71af89571aafb9b2454f7f4d921441885aa84494a60cfd3a1986082c914d87f6https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=72474cf80f87730041c470a7ce2b3148ecfd9006f9f23baeff6fb826f32bd25fhttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=75c210e7273770adb693e52660a3cdadd345cb8e1b2fd5f2e30155692aec5f29https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=95d32a013513de05fb47f154a96a8b24d81e8adc732a9df776e0fc04164e8051https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=99fb5fe2775f597fa4df481491f9f4486ea807374f6298ddf4c28b4f03f3746bhttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=a200c9807f7198b9d99dc70e8a9d975708d10756917feecbdcd4bef63d6b03a4https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=a6333b33dcb11edf6f393e0b484e29055d2bf84ae457b60daf778e3e1fdfdb04https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=ab9729fe417733277d7310e850bf8fb51579c293494f22114c87a9e579f58771https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=b4f088fa8ea92e5ba6c18a09edd4900527bb27ba6b2b3754c3dba101fabf970dhttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=bab81259a168fe63855648f04ba056706705ac94350298aafe7939323315a719https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=d1c7cec8e7bf26ae9bc3e9f65c9f2508a6f41c44c98fe00b501e029837cebb62https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=f178c08b9ba441f82dd8ec78c541e40a5d063bce9e81e620e42b4d50104a84d6https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=f22da7c77f1a16998b98b8588dcd69cd05a1c8117831df3811d18feecfa8340ahttps://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=f6d9d674671389beb6c09a27092e39da11972870063b8c8f9ab48ce9ef8da711https://benchmarkregistry.org/benchmarks/mcp-atlas/public-april-2026?view=history&result=fbcd87496cecdf44e85263f948479daa6635f72654b0e726d111fd5cd2384e2fhttps://benchmarkregistry.org/benchmarks/medxpertqahttps://benchmarkregistry.org/benchmarks/medxpertqa/mmhttps://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=0a9b2dead11a09839d34307e599f93ff134e602cd72e358479627d9eccbc5ac9https://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=2dc2f43ab7ae15ae5a3e647b4871f87e7198286b579f815eee3dbc9994e22b18https://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=399ccf0cb23cf24d936210b4fe2ac51359d1b434069a11ede7ec3621ca0e147dhttps://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=44995bd326dd96792e0e047f7dc4b02ffc0703789c43e925f473a6be85bca062https://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=9765b8b1fc64e4e26f99957df781309a1bfe0ee9423f677ab0d5f21cd8a574edhttps://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=9a5315b00945be2e7b0ec4665afd644e42cb40b3ba9e901d25bf256819bf87c3https://benchmarkregistry.org/benchmarks/medxpertqa/mm?view=history&result=ab8fa2c260def6167385b9dea31515bcdbbd0c6f680a2e14b9958bf56a077b62https://benchmarkregistry.org/benchmarks/mmluhttps://benchmarkregistry.org/benchmarks/mmlu-prohttps://benchmarkregistry.org/benchmarks/mmlu-pro/originalhttps://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=090dcd7c8ec79a22aceb8e284fc6eedb5a39c2a48fc281d12f0cb59a74e79d45https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=1c4b3a28154954694d3395e9a7abb83021a67484af29876732a2daf94e067059https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=2880f9f14751f5b7fe50461b3d588fcc395db55a1012bc79c619d77c75d4c0dchttps://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=2cd040d1578e7a3d71d91c7d3297ef372649dc9203f9a2c294b3bcdd12ca33e8https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=4055b7df261c59b2523ec84e5a49d1db523731830871a06fc20039d8476adec8https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=5f9b7184cdf3c3687901a3813b84a711a7ec7bf6ed990469ab4bc06e2dbcbac8https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=89668e540ffd0c6080a94b092e2df01e06eafa937864cff86eeeb3fc912ac18bhttps://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=9754c9b9e6f9bbea83e22286fca2d933656082e95ace5418bbd8b8369699f55ahttps://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=9c366c34c0773c72b1fede46305571c56ded0c1092c0bc5bcca9b6491098f396https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=b9987b52563f769af1f8ae8e77755c7ec02dbce5bb0a1723a3cd6a86b8312fechttps://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=c0ddf9833ef2580b334bd999587d4ce3f82c9c62e2891220cdb7c08e1b8fbb40https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=c8b794f9289c5b3a83851656660d5ad0ff1d5948b5c5cc32ba4f175e20713a04https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=d8a4c9c095e06cf968854de94bcb523cb47037fb2d7d2a996410ca29ce9d4ebahttps://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=deac5967f6cfc3762b1c78159615586116c8e9656d57a1cacba8f1843d3a77f2https://benchmarkregistry.org/benchmarks/mmlu-pro/original?view=history&result=f2d2d5161a07c80d4d89d028c581ee16d5dce497e20b9f5f89ff47ff6d7bf090https://benchmarkregistry.org/benchmarks/mmlu/mmluhttps://benchmarkregistry.org/benchmarks/mmlu/mmlu?view=history&result=3e0785bb54144ab472e25d5bc422a9bc6e5b01b5aef99e8768156aeccf517868https://benchmarkregistry.org/benchmarks/mmlu/mmlu?view=history&result=950ef1cc69fd17c066f0d0c575ec2591b15278f65fd2c5d23ff0e93e95a1177bhttps://benchmarkregistry.org/benchmarks/mmmuhttps://benchmarkregistry.org/benchmarks/mmmu-prohttps://benchmarkregistry.org/benchmarks/mmmu-pro/no-toolshttps://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=071eacebd6c6d46ff60225e423e81e8625eb8f0cd5bd83c2b7a61b8555d1c47ehttps://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=0d65f78673466470cb08ec39398d0232b1abfa3a984ac8f19e7a4f8331d71694https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=394b1bd08ed7be68880205945fb6732ba366efdafc22731062ed6f7534e29d43https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=8ac087d7dc1796ac008f395b67c03b0fef563f8d75f682255327f8df8a7902d6https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=a2f0556f0b2aaded55e52f9227619a0a7ee8d5e3e7133f94bf69e3d888423f90https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=a85c34c03a16b28db549f5b34ff45929f080dbcd9e68a7a2f9af5139420f55f4https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=b195b9cd61362ba357db758a66b36456a70d044ea6cdfbd67f97904863acc916https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=b1c14889aacab853164aaf9e850f147f0616152f11c8b93cb77a25bf4e1be643https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=b9519e7fc160c36c54143ede9489370660a5c28ef5bab5cc7fea8ad26b2b49eehttps://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=bc85543eaada39e5deea20b928c1c47c01be5ba324b93f76016a56c01f9e52c0https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=c596d4632ffa0e02f811de3373b43b5c97df2c58ee37af5a65f95e68e15d3da8https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=cb0325992f1794385ce6b39f78e34831aae904e1dd8140d7b3336606406bcc16https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=eba658af4e8f69ea4dd7311bbaf4d1dd281171d876968f8eedd7abbf7d01e1f6https://benchmarkregistry.org/benchmarks/mmmu-pro/no-tools?view=history&result=f692ad9d1327c25049bc4cba2edf12978c050237c1090be5513061fabeaf3426https://benchmarkregistry.org/benchmarks/mmmu-pro/with-pythonhttps://benchmarkregistry.org/benchmarks/mmmu-pro/with-python?view=history&result=2c3091179d0105344a94f43c660650dc88edfa54b339c8af02335f6b14bacde3https://benchmarkregistry.org/benchmarks/mmmu-pro/with-toolshttps://benchmarkregistry.org/benchmarks/mmmu-pro/with-tools?view=history&result=3b0280e7919cfcefd79158861b53fc65342bde5f7494103773553ce2b4d1886bhttps://benchmarkregistry.org/benchmarks/mmmu-pro/with-tools?view=history&result=7aaa80c53bc007c77a33e77ea3bc28c8117f1f7440293cba2fa2f603e65f1575https://benchmarkregistry.org/benchmarks/mmmu-pro/with-tools?view=history&result=8640cbc3f709c8e37617a4b71f34db45db9761bde4fbdfc91f4d4306be31cb33https://benchmarkregistry.org/benchmarks/mmmu-pro/with-tools?view=history&result=93f90c79788958aa6c48a56cfc00a08f7f2c3d95d645d4406fc3a4c323509de6https://benchmarkregistry.org/benchmarks/mmmu-pro/with-tools?view=history&result=ac57e0a81383d93872bf578456e5e92b875b73f7f43675cd383878345160a56bhttps://benchmarkregistry.org/benchmarks/mmmu-pro/with-tools?view=history&result=c34e5942f9b7f024d52b2440b297841e61e1ccb8a42335c02cf8a4c80d5695a8https://benchmarkregistry.org/benchmarks/mmmu/mmmuhttps://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=31544867cd417d6cc426dfc749c16ffdd3885012cf9edbf7811d608751596230https://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=616717b3f9611fd837812bf801a5b9d52fa2204a8cbc233d4f1f68cb6ce937a2https://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=7c4a24ffdd1bf84fd872ce61372069e502bf0d08abc50b6b3af0c27d301c1a4fhttps://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=9236bc93e7f8036d25f15844f69d31bf61959e49265a1dd5055cf1e00435dd71https://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=d0a49fdd40a623b06ec2f43e54b2de4b86575743133b73131de47cee9713b21dhttps://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=d3d04e4a350654baa76f58b2e5a768e8b16fb844c01566590af5c46a76e3e3a0https://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=e919de300a2b429597d4426e269ee34e2c07f062469613338e19270273048244https://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=fc6166bcf19695d2a8625bf1a1ce76e7c472b1466913238cdbc450c51927ea8fhttps://benchmarkregistry.org/benchmarks/mmmu/mmmu?view=history&result=ff65fcce53a507c247cee2a3f0ad67f853aea497dee9a09c212bc6a69fdfe5e8https://benchmarkregistry.org/benchmarks/mmstarhttps://benchmarkregistry.org/benchmarks/mmstar/originalhttps://benchmarkregistry.org/benchmarks/mmstar/original?view=history&result=3195ac2416e989de0f6c8cf83c9ccc69eaa1f48eb02c621ede56e550727a9cc0https://benchmarkregistry.org/benchmarks/mrcrhttps://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-128k-256k-gpt-5-2https://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-128k-256k-gpt-5-2?view=history&result=825421ee0d5f850c07108b8bce68d8472175612e33589a7521c6251362ed545dhttps://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-256k-512k-o200k-basehttps://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-256k-512k-o200k-base?view=history&result=85d3f8b80e0449c0d533861c696e4303e4f51df01bfcbbdae2f00999bc3f1546https://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-256k-512k-o200k-base?view=history&result=a72c43eaf0d711ee9cf88e437cf3cd8cc96ad146411fbd17f73b715ca4451c4ehttps://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-512k-1m-o200k-basehttps://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-512k-1m-o200k-base?view=history&result=39503c42af20318a95386123ed671a943c696ed19501ed67ca083a313301f821https://benchmarkregistry.org/benchmarks/mrcr/v2-8-needle-512k-1m-o200k-base?view=history&result=9a1bdf1064e50d63970987c4aa045efe0a425af0e9a04f816e25e1bfdd9b5ae1https://benchmarkregistry.org/benchmarks/multi-swe-benchhttps://benchmarkregistry.org/benchmarks/multi-swe-bench/originalhttps://benchmarkregistry.org/benchmarks/multi-swe-bench/original?view=history&result=c6ffe6eee9ecc2940a1d4103ccbf5948bf5b0aa4a4ce814a41cad934fad6e5b4https://benchmarkregistry.org/benchmarks/nl2repohttps://benchmarkregistry.org/benchmarks/nl2repo/originalhttps://benchmarkregistry.org/benchmarks/nl2repo/original?view=history&result=0560da34529c66f8e7ed4905116cf7cc06aa9ae6e7264bc7088524b58a07a965https://benchmarkregistry.org/benchmarks/nl2repo/original?view=history&result=1f9f56590a579d61408c1834dca661d9868b25f3ebabb4199c6ef727ca28251dhttps://benchmarkregistry.org/benchmarks/nl2repo/original?view=history&result=3bd4b4dfeb92a1818b820086e4479e0157393af45e9c8552adc7bf0668c084fdhttps://benchmarkregistry.org/benchmarks/nl2repo/original?view=history&result=875684ec52f07af28a83a1d14e6d56bed2b0c425bfbd60f8485767edd72ac0d4https://benchmarkregistry.org/benchmarks/ocrbenchhttps://benchmarkregistry.org/benchmarks/ocrbench/originalhttps://benchmarkregistry.org/benchmarks/ocrbench/original?view=history&result=f07fed621f5e7cb55a26940da31cb2dd731147f360002a52342b06817277b8a6https://benchmarkregistry.org/benchmarks/osworldhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.06.24-binaryhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.06.24-binary?view=history&result=e2194dbec95af98ce277e8ce660be4f3b858819b3246c448839bf2ff6e21cbf8https://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.06.24-partialhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.06.24-partial?view=history&result=ee5747918092f8e5e30151c69de3e3e12344ac0fb5edfc2fd4a493b10989313ehttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-binaryhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-binary?view=history&result=7def67d66f92f41352dfdb020197d944e86dd5306cf5a264287e6f70a21c0c23https://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-offline-partialhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-offline-partial?view=history&result=493083de6115a7e72b8bfaaf45a9c346cf68f4e2ac8a0d33d4ecad353dec2b0fhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-offline-partial?view=history&result=e6a65a690a3e46c6cef1c4404ec73b6c301516b63062c5c3a52f2b6d43b07205https://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-partialhttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-partial?view=history&result=765f5623ea10544c32ed761edf8dab6c55f4a8746ace09880af5281e6c37d055https://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-partial?view=history&result=b543dc10d768a717ab81ebfe4e02ae39e7aa5815044c8bc4e1f6325062d4b1b4https://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-stricthttps://benchmarkregistry.org/benchmarks/osworld/2.0-v2026.08.08-strict?view=history&result=da9e77e74c33c472b4a1e21d70a28608c28bba7fdb0e376407da408f96bec166https://benchmarkregistry.org/benchmarks/osworld/verifiedhttps://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=320027a25e0f3a8de1863fdc730bef36f3b483e9eb89648a9782ecca05411d08https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=3c01385de3d17003579c766060b40bf9c777157bbb882895e622074fac5a47cehttps://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=42ea7a5ce728513aed2e9bbd1fe52cbf7d772a1910c2bcda809e61dfd455bb61https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=85035dd35dd837e2f125556e410e56fd5862d9b448e33fb239c29af17cb4dcf9https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=8f1f2301546802f07ae3865233982e436f0a4ac2499f5b046b1eebf194c13035https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=8f466deac455f8a3cccb327636c3427aba15ee9f931a34cde06e4f3bb030f117https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=90b0d0e36659f3987ab70d22722c1c6f3ffd53810410d64a9a7407aee6b99256https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=a1a5786308d9a9d1fc0f39155a0ecd84fad816616910e55eb7c0dcd8c6de63e3https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=b3a22fc3b2b17dd99b72db69cd16dcf7041ec50bcbb414c44545b878574d92fahttps://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=d80e202ccd297f01eeedff91e69334f617756fe1cee0efb791ac1fd4acee7faahttps://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=daf2e068e9bf9ef9b656b9470462d2d3ee59ed45777051c493e309b1787d1d3ehttps://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=deb1516d7969e36a998f7999fa76043781eddfbfc72620fd682cba575b961094https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=eb14713880a6758a25c8da661d3c2d5cc7b18c4a7f53a676984c9e11d9d93a88https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=eda0e6d8a29b099d9599224c7b166feef2d25569aab5159f08e23f53eb4fab54https://benchmarkregistry.org/benchmarks/osworld/verified?view=history&result=f178e5126c6d10907043f9c4d5e9c5984bc13baae26ce0d25fb608421df60864https://benchmarkregistry.org/benchmarks/scicodehttps://benchmarkregistry.org/benchmarks/scicode/originalhttps://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=28e288936cfc4e48943b0baadcb05f1bce6ef06fc9a0a7e7052e238e32e31ce2https://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=3a6043d72ae4e9523865e62a057d59c26b20ed7cdff1e86752e7ba122223e1e9https://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=40f239d3f705131370b5d17e8fff92c1b4ac68eef199c41b9d1e7dea5f71c91bhttps://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=58ced8bd51b133c2d6b6c76b919e3c60176406a8aea29c9091ebd117c31df058https://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=7da6c93b82358fa6482f727de862e2a57264ce9bcbe523048ce442ddd41078a1https://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=a74b7a7f809100afdd1a2d3fbdc851a0ff38d8661c41cab3251f4f5388a2bc12https://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=a8f164364783a7c5cb570fb47132fbfa3fc3700eed5dd59250def99feeac92e6https://benchmarkregistry.org/benchmarks/scicode/original?view=history&result=aa8414bd0268ed1b0305b518c50c5022a8fd4a9ee466903ae6cdedb3e896a9edhttps://benchmarkregistry.org/benchmarks/simpleqa-verifiedhttps://benchmarkregistry.org/benchmarks/simpleqa-verified/originalhttps://benchmarkregistry.org/benchmarks/simpleqa-verified/original?view=history&result=bb5bf478f6bbae8ae707b80b8f813a870f9a64861db13cea0a17ecaec3f84e67https://benchmarkregistry.org/benchmarks/simpleqa-verified/original?view=history&result=d5341461780dbc993c674432575c975e42193025ce001cca744dc205473b25bdhttps://benchmarkregistry.org/benchmarks/skillsbenchhttps://benchmarkregistry.org/benchmarks/skillsbench/78-task-self-contained-opencodehttps://benchmarkregistry.org/benchmarks/skillsbench/78-task-self-contained-opencode?view=history&result=6a0d82f30a15c71881bb36267d98bbcae4162fcff4cb72e42d4165665f58751fhttps://benchmarkregistry.org/benchmarks/skillsbench/78-task-self-contained-opencode?view=history&result=8ccebe8221dd8a9a9fc95e4450a9a7bd5c1dec94352d5d171d559f27ac589091https://benchmarkregistry.org/benchmarks/skillsbench/78-task-self-contained-opencode?view=history&result=f91598fb50acda906304a3ac5824fb0460a877d5d3e39de6aee441ecfb227637https://benchmarkregistry.org/benchmarks/skillsbench/86-task-with-skillshttps://benchmarkregistry.org/benchmarks/skillsbench/86-task-with-skills?view=history&result=313168ab0686c61cefd1ae186b5d4f088e9aec2c8f98dcd281b41acefcb9d221https://benchmarkregistry.org/benchmarks/strongrejecthttps://benchmarkregistry.org/benchmarks/strongreject/originalhttps://benchmarkregistry.org/benchmarks/strongreject/original?view=history&result=335799718499a298b57ed442091c22455883a4a9009dfba34a4a383ba2560da9https://benchmarkregistry.org/benchmarks/strongreject/original?view=history&result=a20d73f11c019c3c5da70094b9a72e26e98ed55338e5730a157364ef8fa79737https://benchmarkregistry.org/benchmarks/swe-atlashttps://benchmarkregistry.org/benchmarks/swe-atlas/codebase-qna-public-mini-swe-agenthttps://benchmarkregistry.org/benchmarks/swe-atlas/codebase-qna-public-mini-swe-agent?view=history&result=3e0e938852f8762ff50b7e7505f3d16036fc4cd2cc61449c48f1fccfe83b4c14https://benchmarkregistry.org/benchmarks/swe-atlas/codebase-qna-public-mini-swe-agent?view=history&result=7f219e65bfa0afb2678b718575b4e9ee137bb7eb63703a6c689a343abdd6a6d2https://benchmarkregistry.org/benchmarks/swe-benchhttps://benchmarkregistry.org/benchmarks/swe-bench-prohttps://benchmarkregistry.org/benchmarks/swe-bench-pro/publichttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public-github-copilothttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public-github-copilot?view=history&result=6c0fb26b6538c4e76e65e1b649586a6c27cfa6d1875da8aae6c2df509802e116https://benchmarkregistry.org/benchmarks/swe-bench-pro/public-qwen-refinedhttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public-qwen-refined?view=history&result=6edb657d3d818cb25cfeb276c5437e8e5ad17a90f9855a2b477a43a216db7845https://benchmarkregistry.org/benchmarks/swe-bench-pro/public-qwen-refined?view=history&result=a7f3964c4a4a0cfea6fbd86c607ebc7db9a667d5b7442bc3cd8977ce135109c3https://benchmarkregistry.org/benchmarks/swe-bench-pro/public-qwen3-6-refinedhttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public-qwen3-6-refined?view=history&result=372b81819fc473e10de75fe49da8e21cbd0a3b6a9fff2ff66cd1f1555e38d53fhttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=0b1484b51d7ecded976bfbd02006f7f67c31f9c6f5e0684066688d4e5c04adb3https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=127f558e6165497de12e2ee7f6a623023a34ef02a49025207bcb3af1e8e292f1https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=1a0fcc352bf1668b96a82413bfbaa1a2cf26b7c2b0370dde92c6486c97547b39https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=1deb0bc13b02c043edda3f0cab5f6260fdf84159b9502b3cc97e9be0b7fa6582https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=310cacedcb4aefdddef2d924ef30fa91ab74f7ea0aeaa9468aaa0c76f0866264https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=39a0ae9128d12fc7aa08b52493b00af4afeed6c9f0d4e8374b023bb59a42532ehttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=39a1e89bcfbf10069bd798d5f7904e3cf5da650ec6bbc57812da28f5f56709bbhttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=3c2c585a6c1c71232e36fd87a2a6f20effa87bedf0bf67410f24a07fe0f0bca9https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=52e6b1c2a90759a85a68af260d46fc6b0d9c1cfda80e6c2ffe86e9eee8819773https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=5737a2774eb2a6153e9fe0d9cb5a5bcdcca6c96c2fc2f46f0d55ff0aeba4297fhttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=72785dde66ce38c32954989dea8e72d4e5063ee939cc676066805ca0fe29de21https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=77880352113bb464499d793a548addf9b1a3a514c63796be3a48a3da18055b54https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=85ec9eb6c7de6aa5c6564f8267c15955745e6792c6ad6bb87ca8b5256fd791b6https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=97d54d2dca6ae4c9c2e70ac1c4517ab5c5fb1f56e5ec715616302dd23fc8e039https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=a2c93a3f3fad1801746ec708b923bfd4f5f13cc8ee01df200d8d564298196116https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=af22d01794d6628083116bd2a7c67034a2b28e01b2441a9452966589619777c5https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=d8cb06ab2ad622b98e20000aa89630c23b7aefdb8ca1f09dea045d4e1fb154f7https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=da84af737021c449ee569c02c3fcc0c011b5045290127156bf83d329f7d82e7chttps://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=e8796b58a10a9a19ef33c1338f1efb662b11e0b34ad005d3f9f281f974777d12https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=e8bf22e39842e74c6c566e467a2af2dce0e4ef7df467607a89f634cea21fd2a4https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=ebc0f78f5a10a416fbb2edd25a85d63579104efe4d8951087c14300e75093d32https://benchmarkregistry.org/benchmarks/swe-bench-pro/public?view=history&result=f048f86e342d69defa7953ec13548ef336cc9e8a890cd2e3af036f4105c5a147https://benchmarkregistry.org/benchmarks/swe-bench/multilingualhttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual-github-copilothttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual-github-copilot?view=history&result=42e6acbc9e6c94a680e31a99164abf243ecdd2194937f769b0679c680b6790bahttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=0b635a7a1d7707dbb1b1c2a93f937fc0ba80235fa9f6d7235c47928c7f633525https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=0c56c313494f9b5a5650ab51af898dfb57583f82d77fa76b0f29fe0955bc39behttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=146a287c87c2a179d48154c90a1f74dfd60dae1282aebd755f0434378ecfba08https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=162b7c7cdf8800395e235471ea37e895c77ef446354cd52153f51e218b7b9fc1https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=2479c4fc9f39653e66b6f54e2156e0e149843ac2cf32fdeabf114a510461ae66https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=2616ad0aac2a023d6cd3ae5c3debab88fb46149f411d980f84a04f531ba20530https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=2d1dc590a225f03a2e0770851181b18c989ea6371eb204e3b8682bddf75ed445https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=3adafe2e24e6483ef6e2c1c7fc36a298f8dba0b6475bc94063064b5a680daff6https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=47004966acdc67f6031358babfd124aa71e5aba45fd2d9087b89ee775f563a0ehttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=477a6430e83f17837f3083ad885a2dd6c97ffcf9a75cb471652a083617717d24https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=51155e7bf4e2aa14d3958a625b836398beee4d75985d05d34c0a6e1248a680c4https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=5826f121ef12ce63a6ea67da6c267eec9800e66484358576b8f1cf71bcb1d145https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=58a3dc796338b5e102aabf2ec73368bd4c4145db2d931e3094b5d47572c6bb7bhttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=5b9fb43027a0b089d506f5f86a4bd1b2b49327ba6dc518eac51619915d15ce03https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=6e563587e771bc53063de24d2259d47de055a6189c8216e12adbcdec66df60f5https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=766b77ecaa8e24723a116216567242af2bf132bdf16c7e0509c3d37bb7d6dab0https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=85a945930fe928937c3334c4d7468f25c236d533af2c039e5748a3949919b88ehttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=9ee4e7c6275ad157cabdb55d1b766af84b2d0fcd6a277d853d92476f623c5ab5https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=a4a340dbc952fed43cf42df4f69f8f32e2ba6fa2a186b558541b60fcf62a4713https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=ab2d94377dcaea2e789270a0136c6034baa0088fe585a549aad196f9d8def6f0https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=c1543af395772a62c63f16a9094dfd27a7cab1c46043998915391256586df5d5https://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=d2c84ed842b5d4897dfc66e2c5a6100fbdeeb43f2e320217c281347e8e04393bhttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=e76c28ea6091c7eb7749f88a936160b351f5c338585024e45be5f284da57131chttps://benchmarkregistry.org/benchmarks/swe-bench/multilingual?view=history&result=fac4988138c3937be2077808f925cafb31e8952fa1ee5186d31fe8b3f6d7e37dhttps://benchmarkregistry.org/benchmarks/swe-bench/verifiedhttps://benchmarkregistry.org/benchmarks/swe-bench/verified-bash-onlyhttps://benchmarkregistry.org/benchmarks/swe-bench/verified-bash-only?view=history&result=0ebf424b14a449ba2fbb7fd486163f2c299a953dd63d4811aa96d79c2d41aff5https://benchmarkregistry.org/benchmarks/swe-bench/verified-bash-only?view=history&result=293439b88ddc9d3d8c74134d7e7faa3a93ffb6876aa686351a52ad884d6b0bc5https://benchmarkregistry.org/benchmarks/swe-bench/verified-droidhttps://benchmarkregistry.org/benchmarks/swe-bench/verified-droid?view=history&result=2c9e7d1f6033c50a62ac365e75bd8c070898bcb379876a88c482440540c5fb4ahttps://benchmarkregistry.org/benchmarks/swe-bench/verified-github-copilothttps://benchmarkregistry.org/benchmarks/swe-bench/verified-github-copilot?view=history&result=65c70acb8fbcb9a4f7c813475728564ee378b16d4a6b2a840f6dfa4bc5676163https://benchmarkregistry.org/benchmarks/swe-bench/verified-opencodehttps://benchmarkregistry.org/benchmarks/swe-bench/verified-opencode?view=history&result=2d6282f04c6fa255ebe33569540ea4b50fb5af2f9bb479b72d4266ad35229ef3https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=0376c6d34c8b6f09fe024db0af3f2a76c87ac36bd8c03790e882ea07432816b9https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=04de44ce1a810eb10c0d3eeadeda7d6c1d8b9a47e450522073a205c845f51d6dhttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=08c26b5a2e81e0a427f4713448e4405a9c38781d0edb71e9ba57a21e913b4a8bhttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=0cc25ddaa9f5beb5620a58afb29c6468e05263bcdd4ed0fc3288e50a176a9049https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=10dbf3401dc753fd2e241b574179ef203f32914e232943dddc22d1ebb38da6e2https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=11ef5aa35ff8567b78b2607d14e96925a6548c0119ba5a28afabcb4fa17d4f4dhttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=141017da7ea46d302a27c728b7e56e08c058d09528c517f898ae93dd4ba2a57ehttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=1d627149c14a65a1e041cf0155acfbbd9d9fbdd99d38f7dd540942a3fadea50ehttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=2134fff6c31a108b4d875838a1f8151b06da20ff374727538c2b0ea8a1a5357ehttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=2c0a325d60e44f5bf284f4adb5f282f5dbcfc29dbd278fda79e27bd386e3f1afhttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=360e12d23f1aa69e39b3b7db5ea5e3a4115fda7893342a558f7c55e0745dd56ehttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=377dd57e6fc3a8cfbc9821a634c154eeec85ea9ed258423ea83ada2e8ced32b3https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=3a9e7c51a47558890849f8d471e762543f104a6ec72be5b426ceb18440b0d5e0https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=3c8b0c97095417068a3df2e618e119b7bbf651fd96494e5ab25d6869e0826f72https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=457c4bbe9d5c64bfaf703281b6fb89e0a01ad44ca0710073bcd06166843d4d89https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=45d5f3301dca05b29135c64263a43b6cb52bbc1f7beff482639438aaa3093297https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=686e948add7119961856b75f5ce152a76e60ef8af3e30216fd01ba8caa3ce163https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=6fdb2c362b5eea0ac3aa41f734ec1140b61b2db460de4009ce297828bb233cd0https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=6fe82f350b5b7ff418c121f466d7f892e5743788a4edb169630718e5d2278d2dhttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=77cfdde247f86247788bf6c91da1442826997dd5b84930a9f942a858ca9f8ad2https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=7a20fd3bea39d8bffe2c1d86e70ddfcc43a0a113ab07b67fb67d64e0889909b2https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=82b9bfd250a839f10fdda6a8471d865aac868e4c6a1bd4086dd3ef7e6ec029achttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=8a2160007ebb7d21840183c4efe9a83d2427b510e5b6b1a1ccd34a47c2abf29ehttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=929d0f51190365122d325f7d74ea47d49a04c05b5281df2c81725fa8ee312c61https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=92f509eb3daebed244dcfcb3cd114367c037599b450b771e5c4a54adc0cc2219https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=9a52a2f4b0f28e04bf19a249c3b0e810cb6946e487801d3441fbdac8148f8de0https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=9d0ae59eee810afc473d74aab3fe9d12725a080668073ccd126f33b4231febe5https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=a58288a9809a390534413a78290bc7b807aca0596e2c30860e24885d88725d9bhttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=aa1a4247d6a76b4eb93f25e4d239bfa6eeb5b00a4ba16e216879cfc568f3fcc1https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=ac57a04e875984b2b03b017e1324de31b63dd1c598f2ccf0c7f321c994f3e878https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=b7c47a5c9cfa965a91de55e14c40aa18ef3ec1d282b8b251db81850a7edbeea9https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=b85fa83581f45c01beb1ad2ac8a2db94e44d4c7167f82e98cc7e95e5e6522725https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=bfb0408f689e9ee6c99bde5bfe875b08814692769230f82f46dcb5b48267bde0https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=c123d71355175331ba983f688546ec362b6c96014ffb2ae86a54caf98bcfaad7https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=c5f0436c9cade27f591860a918ed89918b80209d3d96ff8d1460bb5f6876e8dahttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=cdb779a24c509127b00ba249f30c17a66ce9088bc46a0c92326e41a4ceca0b13https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=ded2368fc42bea1c38f8d84a7f355de14c5d1eba81b8201c0bc320fe42f0e165https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=eb00a5b273a4f42fd618123ccc2322af75722d0c34c874a1e13d1c4b3b3008c5https://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=f7ef83b0adbef5ef7c2d6e53f96907845cfd45d7ede2f43fbf83306ea75ab6eahttps://benchmarkregistry.org/benchmarks/swe-bench/verified?view=history&result=faebf486b3f8ac2deb74448ea9ac55087e11d14123aea25c6016fcc7bfd402e4https://benchmarkregistry.org/benchmarks/swe-fficiencyhttps://benchmarkregistry.org/benchmarks/swe-fficiency/originalhttps://benchmarkregistry.org/benchmarks/swe-fficiency/original?view=history&result=e6195a59d3d1fcf75b23a7ea21371bd476cc896de2ce2dde7928768a6bdce00bhttps://benchmarkregistry.org/benchmarks/tau3-benchhttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-airlinehttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-airline?view=history&result=aef396f5700e6834b15177e073aed02acde102cc6c12feda4f21bd279599d71bhttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-bankinghttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-banking?view=history&result=4922442680e07426254ef73c326c8e04d63b2c59bc9d0d366128f9b192c5402bhttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-retailhttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-retail?view=history&result=2c1a6d57fdac88922a56c66d24812f6214cf245ce731489913a040e57a4e89e4https://benchmarkregistry.org/benchmarks/tau3-bench/tau3-telecomhttps://benchmarkregistry.org/benchmarks/tau3-bench/tau3-telecom?view=history&result=371fabbc76ae11f1fa18483b18d9d0cfafb1e2740b195e04a88c4f38caa15a08https://benchmarkregistry.org/benchmarks/terminal-benchhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-github-copilothttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0-github-copilot?view=history&result=e87f75187abe0bbdcb03bd303dcf045bcc699ebf721c1ce5c4fa35319ea922e8https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-qwen3-6-terminus-2https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-qwen3-6-terminus-2?view=history&result=58db0aa29dbe302c310d3792a561b43fd666c4c617017037ad809eba83b65031https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-qwen3-6-terminus-2?view=history&result=dc72db3734851b944e045b64b2e364e7de05b428d0a794292840018dcf269166https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-qwen3-7-terminus-2-5hhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0-qwen3-7-terminus-2-5h?view=history&result=410462622b167170c464f33967d477dea25fb13fc43ceace0a58b30121fea412https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-qwen3-7-terminus-2-5h?view=history&result=9b33fee9ccbfcbcd135094bad5674e5b542b7a0154ba99c3826b646c46ed0f3ehttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0-terminus-2https://benchmarkregistry.org/benchmarks/terminal-bench/2-0-terminus-2?view=history&result=16a84c33260cd7848dd16acd7155a0ead2750d60798c69041d99afedc785c4b2https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=147a362c1395c64f21532f11adbed0613ee2f64862fbbd86863680eed94dc31ahttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=14c0a8bcc621d4364d20ce5aa8832ee631c97879b0961158bda1aa8207d5a2b7https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=252c14ad5d546625277bf404087e2fbab51a70576cc86f16ccb32a39c6ccd3f1https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=498283a4354e0aa0148424f2a146269c6417a4f9a454fa9d9e0f244780abd0abhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=54102ce3e3a66aa699354d081f48904648337b9f5cec31f1ede13a5caa96716chttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=59400fb32fd7b15b7e48cd77fea2fd959072626fbf1e47e83005f2bded45a580https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=90d10bdb844ae26af15a0dd4db40b706011f9cb1b2b91a09af3f5eaf7b77c8bdhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=910e7bf5d3dfa57b519394be08ddcb9267b829c1d38e8719c805226079ae4627https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=937988fabde57f13a0a6182908ebc733c84bc951c0ad870fb6f9ee74248c04fdhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=ab76cb67e7b4823e015e3b65b59c4a3173c88ad14332f7d03dbbfc98d1172e61https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=b393f7a4ddc0a56c9cee9499151a355452b3296a9a9b709ad5123e18c7b4f6a6https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=cb33522fbbb860caa5784dc20146117a1ae8cac91993e020b768d45071045e63https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=d0bcafd2dd8175f5beb763dc733c42dc273555ada19962b591e9403ae3ea80cdhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=dd5a105b1786f28226bef44642fe566230eb638eb020f02885c2ef9f01c977e7https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=dfb4cf13ba8865d0cd5fd2d07faa3fbc26ab8eb4989d8456a15fdf42c4a1e865https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=e4fde21ba8f29a6ab41acd7b46df3fbe9afce225c7efb947bbb2d47dc6530e1fhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=ec658da81db7b9b286545ec82276e4e8c7f7dff5f87a10c1ee3fae7138b08c4dhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=ef575af0fff5a19f6f8db8fbddaee6d3c31b94c103a2b9ab80710105f1a19213https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=f238c4fa66672fe74cadf17ff125e6d3e4080223f884d1ff2c0d025892e832f0https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=f32d07bb3e935147b002bfbe5deddfa00475fbc7a09aafe605aae8e6295ad921https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=f48da10c24d778a584c3aa0e449346a59bbc36a4425159ad2a2ca6af4908f8achttps://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=f6fbc88a40d0c3368614d3947a84a1329daa070e86893a1968319cdbbfe503e6https://benchmarkregistry.org/benchmarks/terminal-bench/2-0?view=history&result=fdb6be47babf7d90792a3881230979cc8a923b34207fa6e983fc5e8a34bb5b8dhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1https://benchmarkregistry.org/benchmarks/terminal-bench/2-1-claude-codehttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-claude-code?view=history&result=1c9f645442abd09d2a77a732d361bcc8ae2d195fad4d9cb7e1347dad36772194https://benchmarkregistry.org/benchmarks/terminal-bench/2-1-claude-code?view=history&result=36b0c7373510b9219608ca8dca367288eb912fba0fcf96ca7bc1a63a4c98070chttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-mini-swe-agenthttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-mini-swe-agent?view=history&result=fe77da1dd2c1da1c821bcd8b4ae733922393d27f514eb3237c8bb2d5760b829chttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-muse-codehttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-muse-code?view=history&result=aac634fe45153445c8416302cc942527f060497002efc6ed6282b245b1c89c35https://benchmarkregistry.org/benchmarks/terminal-bench/2-1-terminus-2https://benchmarkregistry.org/benchmarks/terminal-bench/2-1-terminus-2?view=history&result=2d41716d562b688877e5c37973efedaf17438b36b5312c7dad2ca16138b67eaehttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-terminus-2?view=history&result=c60df254da2c221dfc3770689da7427a2f1598a22f4ab943fe29fbb5853c474chttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-thinking-machines-internalhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-thinking-machines-internal?view=history&result=4163b60897e04ffd2ed52ec5a8ae3c6e3839460b18e1655473dd0c47db6a82bchttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1-thinking-machines-internal?view=history&result=fbc5a59724f38edcbafdb37e10852ea9438ad247a04b066e84aec8b414b0a66bhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=00b145b9b0435c1f316d29abb6ac5c1849252b17762e22377c12c6f905be5161https://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=1c6e71b1be77ef8e099d6e3cadf86db9b7df6e683561e5d25bade2f30c4ad52dhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=2ae286acbbc6bd794425475794f791db60de4a86b3b1b4a22e2c8b01086685e1https://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=2bf6d40664c05b6df2e6755465d998e1abac03e7c8950d4f53696d674b00b1cahttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=356e1028ad19bca49deb3938b4e4bed4d007fe151d1a11abf5524d91acdadc22https://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=614dc9391ce79fd3b1db93668b31ae5d147bfaf95ec237801797133448b1e9bbhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=66c000771da23074ee8101915cda4c0b7d5343fb213ba8b9153a2bf90abef83chttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=6fb678bb0875146fdda0e4729cc76bd9a03952c4d12d327bc4d728ebacfbb630https://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=795f202e254c1ced613127f1c8ef395584989a484857aba20a5b8d260e965945https://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=7ed9aae6c435809091756e135d299798c7ac473a0eeee072a08df93406f6748fhttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=8faf765d358671c502d20576ca2de399d4ba6aa5c3cd79841559193434e6442chttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=a986b84c960a11564ab2de07cf553164dd2bf41ecbd7948ea74ad3b85e90939ahttps://benchmarkregistry.org/benchmarks/terminal-bench/2-1?view=history&result=fd28da54092f598870bf3d0e1ff6248ea1222cbc15efb034bf956c49012497a6https://benchmarkregistry.org/benchmarks/terminal-bench/4.0https://benchmarkregistry.org/benchmarks/terminal-bench/4.0?view=history&result=066c35fd4bb736b5f50ad61ddf598d0fe28cd5422055e38a51d4cf63d1a4adb1https://benchmarkregistry.org/benchmarks/terminal-bench/4.0?view=history&result=71e556e679745098422b53c5913aee38934182e32f0877947d81d21f40d39e45https://benchmarkregistry.org/benchmarks/terminal-bench/4.0?view=history&result=7c2321bfefd2acfa198c09afdaaa233a1028a9891e49f909e4717f5223139e59https://benchmarkregistry.org/benchmarks/terminal-bench/4.0?view=history&result=a7b4dcf8a22b11e376d3f25a05e13ab42af420e24d06f7330dac15a734e37753https://benchmarkregistry.org/benchmarks/terminal-bench/4.0?view=history&result=bba1ba925ac8b206102bf1de1ac67a9937c1e10e26770fbbf381a026007f0d33https://benchmarkregistry.org/benchmarks/terminal-bench/science-0.1https://benchmarkregistry.org/benchmarks/terminal-bench/science-0.1?view=history&result=49b134c9132a8c50c86ce575df9e819974b1643448b465e2f1673c0d06e83cf2https://benchmarkregistry.org/benchmarks/terminal-bench/science-0.1?view=history&result=d9b1913345541f4685f0ef6bd6f7bd343919d35068e21e228ef938377080c60ahttps://benchmarkregistry.org/benchmarks/terminal-bench/science-0.1?view=history&result=f5b0e0292461dca64f7a017ac0d55947e29df5357af479d649ccfac9f396fcfchttps://benchmarkregistry.org/benchmarks/toolathlonhttps://benchmarkregistry.org/benchmarks/toolathlon/originalhttps://benchmarkregistry.org/benchmarks/toolathlon/original?view=history&result=1614cbfff9f7b250b558127927fafb18472271d6a2e1b741ca784126fb57af31https://benchmarkregistry.org/benchmarks/toolathlon/original?view=history&result=2ca04b32be1b4ef4932b8693e312d85dbf1817a64c61cd265203af519eb799f4https://benchmarkregistry.org/benchmarks/toolathlon/original?view=history&result=aea7a4d11abd7242d82a285abc991bc0a9f14e40379ef74577963ec3dfc25d5chttps://benchmarkregistry.org/benchmarks/toolathlon/original?view=history&result=bb2adaaa7175c60247bada9752b267e9db2dabb7e38d20ff1ba47b25e19f2070https://benchmarkregistry.org/benchmarks/toolathlon/original?view=history&result=fbcf9396c66dc207bec7796566f5b1de332d0c4e2eb40f5be954e7f39cfd3d2dhttps://benchmarkregistry.org/benchmarks/toolathlon/verifiedhttps://benchmarkregistry.org/benchmarks/toolathlon/verified?view=history&result=baa313a2abae55308ae06651f02a77b745d3d04939fb97d55b871966ea1e36a8https://benchmarkregistry.org/benchmarks/toolathlon/verified?view=history&result=c7266a9004dbf1f72bab9fbd2711271f12d53d17af1fbdf56c8dc7e355b3fd7fhttps://benchmarkregistry.org/benchmarks/toolathlon/verified?view=history&result=ddd3ade2e75368e3cf555ddd2f35035bc47c6c9d8f086cb104370b5a33e185f0https://benchmarkregistry.org/benchmarks/toolathlon/verified?view=history&result=e193143aeda1291573355af3076d69df8ceae91759e9ccadacd25c54af499759https://benchmarkregistry.org/benchmarks/toolathlon/verified?view=history&result=f4a1f7bcd11e58868204c36e910bad4a91e3c635162b26843f27d892dd16771ehttps://benchmarkregistry.org/companies/anthropichttps://benchmarkregistry.org/companies/cursorhttps://benchmarkregistry.org/companies/deepseekhttps://benchmarkregistry.org/companies/google-deepmindhttps://benchmarkregistry.org/companies/meta-aihttps://benchmarkregistry.org/companies/microsoft-aihttps://benchmarkregistry.org/companies/minimaxhttps://benchmarkregistry.org/companies/mistralhttps://benchmarkregistry.org/companies/moonshot-aihttps://benchmarkregistry.org/companies/nvidiahttps://benchmarkregistry.org/companies/openaihttps://benchmarkregistry.org/companies/spacexaihttps://benchmarkregistry.org/companies/thinking-machineshttps://benchmarkregistry.org/companies/tongyihttps://benchmarkregistry.org/companies/z-aihttps://benchmarkregistry.org/models/10001https://benchmarkregistry.org/models/10002https://benchmarkregistry.org/models/10003https://benchmarkregistry.org/models/10004https://benchmarkregistry.org/models/10005https://benchmarkregistry.org/models/10006https://benchmarkregistry.org/models/10007https://benchmarkregistry.org/models/10008https://benchmarkregistry.org/models/10009https://benchmarkregistry.org/models/10010https://benchmarkregistry.org/models/10011https://benchmarkregistry.org/models/10012https://benchmarkregistry.org/models/10013https://benchmarkregistry.org/models/10014https://benchmarkregistry.org/models/110001https://benchmarkregistry.org/models/110002https://benchmarkregistry.org/models/120001https://benchmarkregistry.org/models/120002https://benchmarkregistry.org/models/120003https://benchmarkregistry.org/models/130001https://benchmarkregistry.org/models/130002https://benchmarkregistry.org/models/130003https://benchmarkregistry.org/models/130004https://benchmarkregistry.org/models/130005https://benchmarkregistry.org/models/130006https://benchmarkregistry.org/models/130007https://benchmarkregistry.org/models/130008https://benchmarkregistry.org/models/140001https://benchmarkregistry.org/models/140002https://benchmarkregistry.org/models/140003https://benchmarkregistry.org/models/150001https://benchmarkregistry.org/models/150002https://benchmarkregistry.org/models/150003https://benchmarkregistry.org/models/150004https://benchmarkregistry.org/models/150005https://benchmarkregistry.org/models/150006https://benchmarkregistry.org/models/15001https://benchmarkregistry.org/models/160001https://benchmarkregistry.org/models/160002https://benchmarkregistry.org/models/20001https://benchmarkregistry.org/models/20002https://benchmarkregistry.org/models/20003https://benchmarkregistry.org/models/20004https://benchmarkregistry.org/models/20005https://benchmarkregistry.org/models/20006https://benchmarkregistry.org/models/20007https://benchmarkregistry.org/models/20008https://benchmarkregistry.org/models/20009https://benchmarkregistry.org/models/20010https://benchmarkregistry.org/models/20011https://benchmarkregistry.org/models/20012https://benchmarkregistry.org/models/20013https://benchmarkregistry.org/models/20014https://benchmarkregistry.org/models/20015https://benchmarkregistry.org/models/30001https://benchmarkregistry.org/models/30002https://benchmarkregistry.org/models/30003https://benchmarkregistry.org/models/30004https://benchmarkregistry.org/models/30005https://benchmarkregistry.org/models/30006https://benchmarkregistry.org/models/30007https://benchmarkregistry.org/models/30008https://benchmarkregistry.org/models/30009https://benchmarkregistry.org/models/30010https://benchmarkregistry.org/models/35001https://benchmarkregistry.org/models/35002https://benchmarkregistry.org/models/35003https://benchmarkregistry.org/models/35004https://benchmarkregistry.org/models/35005https://benchmarkregistry.org/models/40001https://benchmarkregistry.org/models/40002https://benchmarkregistry.org/models/40003https://benchmarkregistry.org/models/50001https://benchmarkregistry.org/models/50002https://benchmarkregistry.org/models/50003https://benchmarkregistry.org/models/50004https://benchmarkregistry.org/models/60001https://benchmarkregistry.org/models/60002https://benchmarkregistry.org/models/60003https://benchmarkregistry.org/models/70001https://benchmarkregistry.org/models/70002https://benchmarkregistry.org/models/70003https://benchmarkregistry.org/models/80001https://benchmarkregistry.org/models/80002https://benchmarkregistry.org/models/80003https://benchmarkregistry.org/models/80004https://benchmarkregistry.org/models/80005https://benchmarkregistry.org/models/90001https://benchmarkregistry.org/models/90002https://benchmarkregistry.org/models/90003https://benchmarkregistry.org/models/90004https://benchmarkregistry.org/models/90005