List your company

Agent Task Completion on PinchBench

88.7Pass@1Gemini-3-Flash
47.82858.43969.0579.661Apr 29, 2026

Evaluation results

MethodLinks
Gemini-3-FlashModel Group=Proprietary Frontier Models, Context Length=64K2026.0488.7
ClawGym-30A3BModel Group=ClawGym-Agents, Context Length=64K2026.0486
MiniMax-M2.7Model Group=Open-Weight Frontier Models, Context Length=64K2026.0480.9
Claude-4.7-OpusModel Group=Proprietary Frontier Models, Context Length=64K2026.0479.4
Claude-4.6-SonnetModel Group=Proprietary Frontier Models, Context Length=64K2026.0479.3
Qwen3.5-PlusModel Group=Open-Weight Frontier Models, Context Length=64K2026.0478.7
GLM-5.1Model Group=Open-Weight Frontier Models, Context Length=64K2026.0476.4
ClawGym-4BModel Group=ClawGym-Agents, Context Length=64K2026.0476.4
ClawGym-8BModel Group=ClawGym-Agents, Context Length=64K2026.0475.7
Claude-4.6-OpusModel Group=Proprietary Frontier Models, Context Length=64K2026.0475.3
GPT-5.4Model Group=Proprietary Frontier Models, Context Length=64K2026.0468.3
Kimi-K2.6Model Group=Open-Weight Frontier Models, Context Length=64K2026.0466.5
DeepSeek-V3.2Model Group=Open-Weight Frontier Models, Context Length=64K2026.0460.8
Qwen3-235A23BModel Group=Compact Open-Weight Models, Context Length=64K2026.0460.6
Qwen3-30A3BModel Group=Compact Open-Weight Models, Context Length=64K2026.0455.6
Qwen3-8BModel Group=Compact Open-Weight Models, Context Length=64K2026.0454.5
Qwen3-32BModel Group=Compact Open-Weight Models, Context Length=64K2026.0449.4