List your company

Software Engineering on SWE-Bench Pro 1.0 (test)

51.6Resolved RateClaude-Opus-4.5
31.63236.8164247.184Feb 28, 2026

Evaluation results

MethodLinks
Claude-Opus-4.5Size=?, Scaffold=SWE-Agent, Max turns=3002026.0251.6
Claude-Sonnet-4.5Size=?, Scaffold=SWE-Agent, Max turns=3002026.0250.5
Claude-Opus-4.5Size=?, Scaffold=MiniSWE-Agent, Max turns=3002026.0250.2
Kimi-K2.5Size=1000A32, Scaffold=SWE-Agent, Max turns=3002026.0247.3
DeepSeek-V3.2Size=671A37, Scaffold=SWE-Agent, Max turns=3002026.0246
GLM-4.7Size=358A32, Scaffold=SWE-Agent, Max turns=3002026.0245.1
Claude-Sonnet-4.5Size=?, Scaffold=MiniSWE-Agent, Max turns=3002026.0243
Kimi-K2.5Size=1000A32, Scaffold=MiniSWE-Agent, Max turns=3002026.0242.8
Qwen3-Coder-NextSize=80A3, Scaffold=SWE-Agent, Max turns=3002026.0242.7
MiniMax-M2.1Size=230A10, Scaffold=SWE-Agent, Max turns=3002026.0240.8
GLM-4.7Size=358A32, Scaffold=MiniSWE-Agent, Max turns=3002026.0239.4
MiniMax-M2.1Size=230A10, Scaffold=MiniSWE-Agent, Max turns=3002026.0239.1
Qwen3-Coder-NextSize=80A3, Scaffold=MiniSWE-Agent, Max turns=3002026.0238.7
DeepSeek-V3.2Size=671A37, Scaffold=MiniSWE-Agent, Max turns=3002026.0232.4