List your company

Software Engineering on SWE-Bench Pro (public)

64.3Resolve Rate (Pass@1)Claude Opus 4.7
41.83647.66853.559.332Dec 11, 2025Jan 10, 2026Feb 9, 2026Mar 12, 2026Apr 11, 2026May 11, 2026Jun 11, 2026

Evaluation results

MethodLinks
Claude Opus 4.7Harness=Proprietary2026.0664.3———————————
GPT-5.4Harness=MSA2026.0659.1———————————
CCABackbone Model=GPT-5.22025.1259———————————
OpenAIBackbone Model=GPT-5.22025.1256———————————
CCABackbone Model=Claude 4.5 Opus2025.1254.3———————————
Gemini 3.1 ProHarness=Proprietary2026.0654.2———————————
CCABackbone Model=Claude 4.5 Sonnet2025.1252.7———————————
AnthropicBackbone Model=Claude 4.5 Opus2025.1252———————————
Claude Opus 4.6Harness=MSA2026.0651.9———————————
Qwen3.5-397B-A17BHarness=Proprietary2026.0650.9———————————
SkillsVoteBackbone Family=Codex, Backbone=GPT-5.2 Medium, Setting=Online2026.0550.256.263.768.432.935.556.545.638.55072.70
SkillsVoteBackbone Family=Codex, Backbone=GPT-5.4 mini Medium, Setting=Online2026.05495159.368.432.938.256.549.138.551.861.40
GPT-5.2 MediumBackbone Family=Codex, Setting=Baseline2026.0547.64964.86232.934.254.849.143.15047.70
GPT-5.4 mini MediumBackbone Family=Codex, Setting=Baseline2026.0546.952.15564.631.835.55050.938.546.461.40
Gemini 3.1 ProHarness=MSA2026.0646.1———————————
Live-SWE-AgentBackbone Model=Claude 4.5 Sonnet2025.1245.8———————————
CCABackbone Model=Claude 4 Sonnet2025.1245.5———————————
SWE-AgentBackbone Model=Claude 4.5 Sonnet2025.1243.6———————————
SWE-AgentBackbone Model=Claude 4 Sonnet2025.1242.7———————————