List your company

Code Generation on SWE-bench Verified

77Pass@3MTL (T)
52.0458.526571.48Apr 15, 2026

Evaluation results

MethodLinks
MTL (T)Model=GPT-5-mini, Method=MTL (T)2026.0477
MTL (W)Model=GPT-5-mini, Method=MTL (W)2026.0477
MTL (I)Model=GPT-5-mini, Method=MTL (I)2026.0477
MTL (S)Model=GPT-5-mini, Method=MTL (S)2026.0476
Zero-shotModel=GPT-5-mini, Method=Zero-shot2026.0473
MTL (I)Model=Qwen3-Coder-480B-A35B-Instruct, Method=MTL (I)2026.0462
MTL (I)Model=DeepSeek V3.2, Method=MTL (I)2026.0459
Zero-shotModel=Qwen3-Coder-480B-A35B-Instruct, Method=Zero-shot2026.0459
Zero-shotModel=DeepSeek V3.2, Method=Zero-shot2026.0453