SWE-bench

Benchmark Family
SWE-bench
Organization
Princeton University
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedswe-bench/defaultACTIVE0
Multilingualswe-bench/multilingualACTIVE6
Multimodalswe-bench/multimodalACTIVE2
Proswe-bench/proACTIVE9
Verifiedswe-bench/verifiedACTIVE7
Verified Hardswe-bench/verified-hardACTIVE1

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-00155-001 GPT-5.5 SWE-bench Pro Resolved 58.6 Unknown Primary source OPNAI-55
BR-002O47-001 Claude Opus 4.7 SWE-bench Verified Resolved 87.6% Unknown Primary source ANTHR-O47
BR-002O47-002 Claude Opus 4.7 SWE-bench Pro Resolved 64.3% Unknown Primary source ANTHR-O47
BR-002O47-003 Claude Opus 4.7 SWE-bench Multilingual Resolved 80.5% Unknown Primary source ANTHR-O47
BR-002O47-004 Claude Opus 4.7 SWE-bench Multimodal Resolved 34.5% Unknown Primary source ANTHR-O47
BR-002O48-001 Claude Opus 4.8 SWE-bench Verified Resolved 88.6 Unknown Primary source ANTHR-O48
BR-002O48-002 Claude Opus 4.8 SWE-bench Pro Resolved 69.2 Unknown Primary source ANTHR-O48
BR-002O48-003 Claude Opus 4.8 SWE-bench Multilingual Resolved 84.4 Unknown Primary source ANTHR-O48
BR-002O48-004 Claude Opus 4.8 SWE-bench Multimodal Resolved 38.4 Unknown Primary source ANTHR-O48
BR-00331P-003 Gemini 3.1 Pro SWE-bench Verified Resolved 80.6% Unknown Primary source GOOGL-G31P
BR-00331P-007 Gemini 3.1 Pro SWE-bench Pro Resolved 54.2% Unknown Primary source GOOGL-G31P
BR-005C2-002 Composer 2 SWE-bench Multilingual Resolved 73.7 Unknown Primary source CURSR-C2
BR-00735-028 Qwen3.5-397B-A17B SWE-bench Verified Resolved 76.4 Unknown Primary source QWEN-35
BR-00735-029 Qwen3.5-397B-A17B SWE-bench Multilingual Resolved 69.3 Unknown Primary source QWEN-35
BR-00737-009 Qwen3.7-Max SWE-bench Pro Resolved 60.6 Unknown Primary source QWEN-37
BR-008V4FLASH-015 DeepSeek V4-Flash SWE-bench Verified Resolved 79.0 Unknown Primary source DPSK-V4FLASH
BR-008V4FLASH-016 DeepSeek V4-Flash SWE-bench Pro Resolved 52.6 Unknown Primary source DPSK-V4FLASH
BR-008V4FLASH-017 DeepSeek V4-Flash SWE-bench Multilingual Resolved 73.3 Unknown Primary source DPSK-V4FLASH
BR-008V4PRO-015 DeepSeek V4-Pro SWE-bench Verified Resolved 80.6 Unknown Primary source DPSK-V4PRO
BR-008V4PRO-016 DeepSeek V4-Pro SWE-bench Pro Resolved 55.4 Unknown Primary source DPSK-V4PRO
BR-008V4PRO-017 DeepSeek V4-Pro SWE-bench Multilingual Resolved 76.2 Unknown Primary source DPSK-V4PRO
BR-009MS11-001 Muse Spark 1.1 SWE-bench Verified Hard Resolved 24/42 Unknown Primary source META-MS11
BR-01152-010 GLM-5.2 SWE-bench Pro Resolved 62.1 Unknown Primary source GLM-52
BR-012M3-002 MiniMax-M3 SWE-bench Pro Resolved 59 Unknown Primary source MMAX-M3
BR-012M3-004 MiniMax-M3 SWE-bench Verified Resolved 80.5 Unknown Primary source MMAX-M3