List your company

Code Generation on HumanEval (pass@1, pass@2)

86pass@1EXG-SE
14.96833.40951.8570.291May 18, 2026

Evaluation results

MethodLinks
EXG-SEModel=Qwen3-Coder-Flash2026.058695.1
EXG-SE-RevModel=Qwen3-Coder-Flash2026.0583.592.1
EXG-ReflexionModel=Qwen3-Coder-Flash2026.0581.787.2
EXGModel=Qwen3-Coder-Flash2026.0580.583.5
SE-Agent-RevModel=Qwen3-Coder-Flash2026.056494.5
SE-AgentModel=Qwen3-Coder-Flash2026.0559.893.9
EXG-SE-RevModel=Qwen3-8B2026.0559.179.9
ReflexionModel=Qwen3-Coder-Flash2026.0558.578
EXG-ReflexionModel=Qwen3-1.7B2026.0557.369.5
EXG-SEModel=Qwen3-8B2026.0557.383.5
EXGModel=Qwen3-1.7B2026.0553.758.5
EXG-SE-RevModel=Qwen3-1.7B2026.0553.759.8
EXG-SEModel=Qwen3-1.7B2026.0551.261
EXG-ReflexionModel=Qwen3-8B2026.0550.672
EXGModel=Qwen3-8B2026.0541.548.8
ReflexionModel=Qwen3-1.7B2026.0520.754.3
SE-Agent-RevModel=Qwen3-1.7B2026.0520.756.1
ReflexionModel=Qwen3-8B2026.0520.161
SE-AgentModel=Qwen3-1.7B2026.0519.552.4
SE-Agent-RevModel=Qwen3-8B2026.0518.982.3
SE-AgentModel=Qwen3-8B2026.0517.772