PinchBench - 147 Tasks - OpenClaw 2026.5.20 (e510042): leaderboard
Metric: Best Official Run Score (%). Source: pinchbench.com. Saturation forecast: Not forecast. 39 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | MiMo-V2.5 | 91.87 |
| 2 | DeepSeek V4 Flash | 91.46 |
| 3 | Grok 4.5 | 91.17 |
| 4 | Claude Opus 4.7 | 91.11 |
| 5 | GPT-5.6 Luna | 90.79 |
| 6 | Claude Haiku 4.5 | 88.26 |
| 7 | Claude Opus 4.6 | 87.97 |
| 8 | Grok 4.20 | 87.78 |
| 9 | GPT-5.6 Sol | 87 |
| 10 | MiMo-V2.5-Pro | 86.25 |
| 11 | GLM-5V Turbo | 85.33 |
| 12 | Grok 4.3 | 85.01 |
| 13 | GLM-5-Turbo | 84.69 |
| 14 | Qwen 3.6 Plus | 84.65 |
| 15 | MiniMax-M2.7 | 84.46 |
Interactive version: theaggregate.ai/benchmark?slug=pinchbench-147-tasks-openclaw-2026-5-20-e510042 · How It Works · Data refreshed daily, snapshot 2026-10-09.