BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Recent Records

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-007QWEN330BA3B2507-014 Qwen3 30B A3B 2507 AA-LCR Overall 59% Unknown Primary source QWEN-QWEN330BA3B2507
BR-008DEEPSEEKR10528QWEN38B-001 DeepSeek R1 0528 Qwen3 8B Artificial Analysis Intelligence Index Overall 10.4 Unknown Primary source DPSK-DEEPSEEKR10528QWEN38B
BR-008DEEPSEEKR10528QWEN38B-002 DeepSeek R1 0528 Qwen3 8B GPQA Diamond Accuracy 61.2% Unknown Primary source DPSK-DEEPSEEKR10528QWEN38B
BR-008DEEPSEEKR10528QWEN38B-003 DeepSeek R1 0528 Qwen3 8B Humanity's Last Exam No tools Overall 5.6% Unknown Primary source DPSK-DEEPSEEKR10528QWEN38B
BR-008DEEPSEEKV4PRO-001 DeepSeek V4-Pro Artificial Analysis Intelligence Index Overall 40.8 Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-002 DeepSeek V4-Pro GPQA Diamond Accuracy 90.5% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-003 DeepSeek V4-Pro Humanity's Last Exam No tools Overall 33.5% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-004 DeepSeek V4-Pro SciCode Overall 46.4% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-005 DeepSeek V4-Pro tau2-bench Overall 94.2% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-006 DeepSeek V4-Pro Terminal-Bench Hard Overall 41.7% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-007 DeepSeek V4-Pro CritPt Overall 10% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-008 DeepSeek V4-Pro AA-Omniscience Overall -9.7 Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-009 DeepSeek V4-Pro AA-Omniscience Accuracy 41.8% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-010 DeepSeek V4-Pro IFBench Overall 71.3% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-011 DeepSeek V4-Pro GDPval-AA Average Normalized Score 39.8% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-012 DeepSeek V4-Pro AA-LCR Overall 65% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-013 DeepSeek V4-Pro Artificial Analysis Intelligence Index Overall 31.2 Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-014 DeepSeek V4-Pro GPQA Diamond Accuracy 71.7% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-015 DeepSeek V4-Pro Humanity's Last Exam No tools Overall 7.7% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-016 DeepSeek V4-Pro SciCode Overall 42.4% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-017 DeepSeek V4-Pro tau2-bench Overall 91.2% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-018 DeepSeek V4-Pro Terminal-Bench Hard Overall 36.4% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-019 DeepSeek V4-Pro CritPt Overall 0.9% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-020 DeepSeek V4-Pro AA-Omniscience Overall -30.1 Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-021 DeepSeek V4-Pro AA-Omniscience Accuracy 30.8% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-022 DeepSeek V4-Pro IFBench Overall 45.8% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-023 DeepSeek V4-Pro AA-LCR Overall 45% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-024 DeepSeek V4-Pro Artificial Analysis Intelligence Index Overall 44.3 Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-025 DeepSeek V4-Pro GPQA Diamond Accuracy 88.8% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-026 DeepSeek V4-Pro Humanity's Last Exam No tools Overall 35.9% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-027 DeepSeek V4-Pro SciCode Overall 50% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-028 DeepSeek V4-Pro tau2-bench Overall 96.2% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-029 DeepSeek V4-Pro tau3-Banking Overall 25.8% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-030 DeepSeek V4-Pro Terminal-Bench Hard Overall 46.2% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-031 DeepSeek V4-Pro Terminal-Bench 2.1 Overall 64% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-032 DeepSeek V4-Pro CritPt Overall 12.9% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-033 DeepSeek V4-Pro AA-Omniscience Overall -10 Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-034 DeepSeek V4-Pro AA-Omniscience Accuracy 43.3% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-035 DeepSeek V4-Pro IFBench Overall 76.5% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-036 DeepSeek V4-Pro APEX-Agents Overall 24.3% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-037 DeepSeek V4-Pro ITBench SRE Overall 38.3% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-038 DeepSeek V4-Pro GDPval-AA Average Normalized Score 40.4% Unknown Primary source DPSK-V4PRO
BR-008DEEPSEEKV4PRO-039 DeepSeek V4-Pro AA-LCR Overall 66.3% Unknown Primary source DPSK-V4PRO
BR-009LLAMA32INSTRUCT11BVISION-001 Llama 3.2 Instruct 11B (Vision) Artificial Analysis Intelligence Index Overall 3.3 Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-002 Llama 3.2 Instruct 11B (Vision) GPQA Diamond Accuracy 22.1% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-003 Llama 3.2 Instruct 11B (Vision) Humanity's Last Exam No tools Overall 5.2% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-004 Llama 3.2 Instruct 11B (Vision) SciCode Overall 11.2% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-005 Llama 3.2 Instruct 11B (Vision) tau2-bench Overall 14.6% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-006 Llama 3.2 Instruct 11B (Vision) Terminal-Bench Hard Overall 0.8% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-007 Llama 3.2 Instruct 11B (Vision) CritPt Overall 0% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-008 Llama 3.2 Instruct 11B (Vision) AA-Omniscience Overall -63.1 Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-009 Llama 3.2 Instruct 11B (Vision) AA-Omniscience Accuracy 10.2% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-010 Llama 3.2 Instruct 11B (Vision) IFBench Overall 30.4% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-011 Llama 3.2 Instruct 11B (Vision) MMMU-Pro Overall 29.3% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT11BVISION-012 Llama 3.2 Instruct 11B (Vision) AA-LCR Overall 11.7% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-017GRANITE40HSMALL-001 Granite 4.0 H Small Artificial Analysis Intelligence Index Overall 5.2 Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-002 Granite 4.0 H Small GPQA Diamond Accuracy 41.6% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-003 Granite 4.0 H Small Humanity's Last Exam No tools Overall 3.7% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-004 Granite 4.0 H Small SciCode Overall 20.9% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-005 Granite 4.0 H Small tau2-bench Overall 17.3% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-006 Granite 4.0 H Small Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-007 Granite 4.0 H Small CritPt Overall 0% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-008 Granite 4.0 H Small AA-Omniscience Overall -60.9 Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-009 Granite 4.0 H Small AA-Omniscience Accuracy 14.4% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-010 Granite 4.0 H Small IFBench Overall 31.5% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-011 Granite 4.0 H Small AA-LCR Overall 9% Unknown Primary source IBM-GRANITE40HSMALL
BR-034TRI21BTHINK-009 Tri-21B-Think AA-Omniscience Accuracy 12% Unknown Primary source TRLN-TRI21BTHINK
BR-034TRI21BTHINK-010 Tri-21B-Think IFBench Overall 54.6% Unknown Primary source TRLN-TRI21BTHINK
BR-034TRI21BTHINK-011 Tri-21B-Think AA-LCR Overall 11% Unknown Primary source TRLN-TRI21BTHINK
BR-00154P-001 GPT-5.4 Pro CritPt Overall 30% Unknown Primary source OPNAI-54P
BR-007QWEN3MAXPREVIEW-001 Qwen3 Max (Preview) Artificial Analysis Intelligence Index Overall 19.2 Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-002 Qwen3 Max (Preview) GPQA Diamond Accuracy 76.4% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-003 Qwen3 Max (Preview) Humanity's Last Exam No tools Overall 9.3% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-004 Qwen3 Max (Preview) SciCode Overall 37% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-005 Qwen3 Max (Preview) tau2-bench Overall 32.7% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-006 Qwen3 Max (Preview) Terminal-Bench Hard Overall 19.7% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-007 Qwen3 Max (Preview) CritPt Overall 0.9% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-008 Qwen3 Max (Preview) AA-Omniscience Overall -40.6 Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-009 Qwen3 Max (Preview) AA-Omniscience Accuracy 24.3% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-010 Qwen3 Max (Preview) IFBench Overall 48% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXPREVIEW-011 Qwen3 Max (Preview) AA-LCR Overall 39.7% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-009LLAMA2CHAT70B-001 Llama 2 Chat 70B Artificial Analysis Intelligence Index Overall 3 Unknown Primary source META-LLAMA2CHAT70B
BR-009LLAMA2CHAT70B-002 Llama 2 Chat 70B GPQA Diamond Accuracy 32.7% Unknown Primary source META-LLAMA2CHAT70B
BR-009LLAMA2CHAT70B-003 Llama 2 Chat 70B Humanity's Last Exam No tools Overall 5% Unknown Primary source META-LLAMA2CHAT70B
BR-010KIMILINEAR48BA3BINSTRUCT-003 Kimi Linear 48B A3B Instruct Humanity's Last Exam No tools Overall 2.7% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-004 Kimi Linear 48B A3B Instruct SciCode Overall 19.9% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-005 Kimi Linear 48B A3B Instruct tau2-bench Overall 0% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-006 Kimi Linear 48B A3B Instruct Terminal-Bench Hard Overall 11.4% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-007 Kimi Linear 48B A3B Instruct IFBench Overall 28.1% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-008 Kimi Linear 48B A3B Instruct AA-LCR Overall 25.7% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-01151-001 GLM-5.1 Artificial Analysis Intelligence Index Overall 40.2 Unknown Primary source GLM-51
BR-01151-002 GLM-5.1 GPQA Diamond Accuracy 86.8% Unknown Primary source GLM-51
BR-01151-003 GLM-5.1 Humanity's Last Exam No tools Overall 28% Unknown Primary source GLM-51
BR-01151-004 GLM-5.1 SciCode Overall 43.8% Unknown Primary source GLM-51
BR-01151-005 GLM-5.1 tau2-bench Overall 97.7% Unknown Primary source GLM-51
BR-01151-006 GLM-5.1 tau3-Banking Overall 11.5% Unknown Primary source GLM-51
BR-01151-007 GLM-5.1 Terminal-Bench Hard Overall 43.2% Unknown Primary source GLM-51
BR-01151-008 GLM-5.1 Terminal-Bench 2.1 Overall 61.8% Unknown Primary source GLM-51
BR-01151-009 GLM-5.1 CritPt Overall 4.6% Unknown Primary source GLM-51
BR-01151-010 GLM-5.1 AA-Omniscience Overall 1.9 Unknown Primary source GLM-51