List your company

Code Evaluation on SWE Verified Agentless

57.6pass@1DeepSeek-R1 0528 671B
19.01629.03339.0549.067Dec 15, 2025

Evaluation results

MethodLinks
DeepSeek-R1 0528 671BParameters=671B, Thinking Mode=true, Setup=Agentless2025.1257.6
Nemotron-Cascade 14B-Thinking (Test-Time Scaling)Parameters=14B, Thinking Mode=true, Test-Time Scaling=true2025.1253.8
Gemini-2.5 Flash-ThinkingThinking Mode=true, Setup=Own scaffolds2025.1248.9
Nemotron Cascade-8B (Test-Time Scaling)Parameters=8B, Thinking Mode=true, Test-Time Scaling=true2025.1243.6
Nemotron-Cascade 14B-ThinkingParameters=14B, Thinking Mode=true, Setup=Agentless2025.1243.1
Nemotron Cascade-8BParameters=8B, Thinking Mode=true, Setup=Agentless2025.1237.2
Qwen3 14BParameters=14B, Setup=Agentless2025.1227.4
Qwen3 8BParameters=8B, Setup=Agentless2025.1220.5