List your company

Iterative Self-Optimization on OPT-BENCH-ML 20 steps 1.0

8Win CountQwen2.5-3B-Instruct
3.844.9267.08May 9, 2026

Evaluation results

MethodLinks
Qwen2.5-3B-InstructSteps=20, Model Category=Open-Source, Model Type=General2026.05838582114
gemini-2.0-flashSteps=20, Model Category=Proprietary, Model Type=General2026.0576104540
claude-3-5-sonnet-20241022Steps=20, Model Category=Proprietary, Model Type=General2026.05718285247
claude-3-7-sonnet-20250219Steps=20, Model Category=Proprietary, Model Type=General2026.0576126658
grok-3Steps=20, Model Category=Proprietary, Model Type=General2026.05612116258
Qwen3-235B-InstructSteps=20, Model Category=Proprietary, Model Type=General2026.0566105755
Internlm3-8b-InstructSteps=20, Model Category=Open-Source, Model Type=General2026.05618202420
Qwen2.5-7B-InstructSteps=20, Model Category=Open-Source, Model Type=General2026.05624283533
Qwen2.5-14B-InstructSteps=20, Model Category=Open-Source, Model Type=General2026.05618184743
Qwen2.5-32B-InstructSteps=20, Model Category=Open-Source, Model Type=General2026.05620205246
Qwen3-30B-A3BSteps=20, Model Category=Open-Source, Model Type=General2026.056006968
gpt-o3-miniSteps=20, Model Category=Proprietary, Model Type=Reasoning2026.055007369
Deepseek-V3.1-ThinkingSteps=20, Model Category=Proprietary, Model Type=Reasoning2026.055007976
Qwen3-235B-ThinkingSteps=20, Model Category=Proprietary, Model Type=Reasoning2026.055007676
Qwen3-8BSteps=20, Model Category=Open-Source, Model Type=General2026.05512206360
Qwen3-32BSteps=20, Model Category=Open-Source, Model Type=General2026.0556106060
gpt-4o-2024-08-06Steps=20, Model Category=Proprietary, Model Type=General2026.05422184754
gpt-4.1-2025-04-14Steps=20, Model Category=Proprietary, Model Type=General2026.054425355
Qwen2.5-72B-InstructSteps=20, Model Category=Open-Source, Model Type=General2026.05422324744