List your company

Software Engineering Issue Resolution on SWE-Bench-Pro (test)

59.9Pass@1GPT-5.4
26.110434.882743.65552.4273Jun 16, 2026

Evaluation results

MethodLinks
GPT-5.4Harness=SSA, Environment=Base public containers2026.0659.964.7757.7
GPT-5.3Harness=SSA, Environment=Base public containers2026.0658.5762.5956.8
Qwen3-Coder NextHarness=SSA, Environment=Base public containers2026.0657.7569.8244.3
Opus 4.6Harness=SSA, Environment=Base public containers2026.0657.4563.153.4
GPT-5.2Harness=SSA, Environment=Base public containers2026.0656.476056
Opus 4.5Harness=SSA, Environment=Base public containers2026.0654.5858.7252
Gemini 3.1 ProHarness=SSA, Environment=Base public containers2026.065458.7254.2
GPT-5.2-codexHarness=SSA, Environment=Base public containers2026.0653.8762.5956.4
Sonnet 4.6Harness=SSA, Environment=Base public containers2026.0653.6759.83—
Grok 4.2Harness=SSA, Environment=Base public containers2026.0651.5757.31—
Qwen3.6 27BHarness=SSA, Environment=Base public containers2026.0651.458.4953.5
Sonnet 4.5Harness=SSA, Environment=Base public containers2026.0650.1556.22—
Gemini 3 FlashHarness=SSA, Environment=Base public containers2026.0649.4355.4—
Qwen3.5 27BHarness=SSA, Environment=Base public containers2026.0647.4454.2251.2
Qwen3.6 35B-A3BHarness=SSA, Environment=Base public containers2026.0646.753.7849.5
Haiku 4.5Harness=SSA, Environment=Base public containers2026.0646.3753.14—
Sonnet 4.0Harness=SSA, Environment=Base public containers2026.0644.2651.09—
GPT-OSS 120BHarness=SSA, Environment=Base public containers2026.0643.6151.1—
GPT-OSS 20BHarness=SSA, Environment=Base public containers2026.0639.6748.22—
Qwen3-Coder 480BHarness=SSA, Environment=Base public containers2026.0638.946.42—
Qwen3-Coder 30BHarness=SSA, Environment=Base public containers2026.0627.4133.96—