List your company

Long-horizon task solving on PINCHBENCH 123 tasks expanded

90.3Best Success RateClaude-Haiku-4.5
19.68438.01756.3574.683Jun 15, 2026

Evaluation results

MethodLinks
Claude-Haiku-4.5Source type=Closed-source models2026.0690.358.9
Claude-Opus-4.6Source type=Closed-source models2026.0688.967.5
Qwen3.6-PlusSource type=Open-source / open-weight models2026.0682.862.6
Gemini-3.1-Pro-PreviewSource type=Closed-source models2026.0681.780.2
OpenClaw-Skill 9BSource type=Open-source / open-weight models2026.0668.253.6
OpenClaw-Skill 4BSource type=Open-source / open-weight models2026.0661.447.6
Qwen3.5-9BSource type=Open-source / open-weight models2026.0661.147.1
Qwen3.5-4BSource type=Open-source / open-weight models2026.0660.945.9
Nemotron-3-Super-120B-A12BSource type=Open-source / open-weight models2026.0650.638.6
GPT-OSS-120BSource type=Open-source / open-weight models2026.0647.444.5
GPT-OSS-20BSource type=Open-source / open-weight models2026.0641.837.5
OpenClaw-Skill-Qwen3 8BSource type=Open-source / open-weight models2026.063322.5
OpenClaw-Skill-Qwen3-4BSource type=Open-source / open-weight models2026.0631.120.8
Qwen3-8BSource type=Open-source / open-weight models2026.0627.918.3
Qwen3-4BSource type=Open-source / open-weight models2026.0622.413.6