Benchmark
PinchBench v2 · Best Success Rate
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 60
- Scores recorded
- 64
- Sources
- 1
- IQ weight
- 1.39
Score distribution
- 79.3%
- Mean
- 85.3%
- Median
- 18.2%
- Std dev
- 58.9%
- 10th percentile
- 91.9%
- 90th percentile
- 3.2%
- Min
This benchmark has a weight of 1.39 for chat models, measured over 50 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Claude Opus 4.6OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 100% |
| 2 | Mercury 2OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 100% |
| 3 | Claude Opus 4.8OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · fast route · best run· Reported by PinchBench· via BenchBoard docs | 94.5% |
| 4 | Qwen3.7 MaxOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 93.4% |
| 5 | Claude Opus 4.6SenseNova 6.7 Flash-Lite official benchmark chart · best result · chart does not restate benchmark version· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 93.3% |
| 6 | MiMo V2.5OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 91.9% |
| 7 | Claude Opus 4.8OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 91.8% |
| 8 | Claude Opus 4.7OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 91.6% |
| 9 | DeepSeek V4 FlashOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 91.5% |
| 10 | Grok 4.5OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 91.2% |
| 11 | GPT-5.6 LunaOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 90.8% |
| 12 | Nemotron 3 UltraOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 90.6% |
| 13 | GPT 5.4SenseNova 6.7 Flash-Lite official benchmark chart · best result · chart does not restate benchmark version· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.5% |
| 14 | Claude Haiku 4.5OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 90.4% |
| 15 | MiMo V2.5 ProOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 89.5% |
| 16 | Qwen3.6 FlashOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 89.1% |
| 17 | GPT 5.5OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 89% |
| 18 | GPT 5.4OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 88.4% |
| 19 | GLM 5.2OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 87.8% |
| 20 | Nemotron 3.5 Lightning 30B A3BOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 87.2% |
| 21 | GPT-5.6 SolOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 87% |
| 22 | GLM 5SenseNova 6.7 Flash-Lite official benchmark chart · best result · chart does not restate benchmark version· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.4% |
| 23 | GPT-5.4 miniOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 86.4% |
| 24 | Qwen3.6 PlusOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 85.9% |
| 25 | Step 3.5 FlashSenseNova 6.7 Flash-Lite official benchmark chart · best result · chart does not restate benchmark version· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.3% |
| 26 | Step 3.5 FlashOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 84.7% |
| 27 | Claude Sonnet 4.6OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 84.6% |
| 28 | MiniMax M2.7OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 84.5% |
| 29 | Devstral 2 123b Instruct 2512OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 83.2% |
| 30 | Gemini 3.1 Pro PreviewOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 82.9% |
| 31 | Kimi K2.5OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 81.9% |
| 32 | DeepSeek V4 Pro 0813OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 81.6% |
| 33 | GPT-5.6 TerraOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 81.4% |
| 34 | Gemini 3.1 Flash LiteOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 80.5% |
| 35 | Kimi K2.7 CodeOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 80.2% |
| 36 | Gemini 3 FlashOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 80% |
| 37 | GPT 5.4 NanoOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 77.3% |
| 38 | Gemma 4 26B A4BOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 77.1% |
| 39 | Gemma 4 31B ITOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 77% |
| 40 | GLM 5.1OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 76.6% |
| 41 | Gemini 3.5 FlashOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 76.3% |
| 42 | Mistral Large 3 675b InstructOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 72.9% |
| 43 | Fugu UltraOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 72.4% |
| 44 | Trinity Large PreviewOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 72.4% |
| 45 | Trinity Large ThinkingOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 71.2% |
| 46 | Nemotron 3 Super 120B A12BOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 60.4% |
| 47 | Claude Fable 5OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 59.6% |
| 48 | Nova 2 LiteOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run, v1· Reported by PinchBench· via BenchBoard docs | 58.9% |
| 49 | Claude Sonnet 4OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 57.8% |
| 50 | GPT OSS 120BOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 47.4% |
Showing 1–50 of 54 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Aion 3.0OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 62.4% |
| GLM 5 TurboOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 88.2% |
| GLM 5V TurboOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 86.6% |
| Grok 4.20OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 87.8% |
| Grok 4.3OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 85% |
| Grok Build 0.1OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 92.1% |
| Ling 2.6 1TOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 82.6% |
| Nemotron 3.5 Bolt 74B-A9B 24GBOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 90.1% |
| Nemotron 3.5 Bolt 74B-A9B BF16OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 91.7% |
| Seed-2.0-LiteOpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run· Reported by PinchBench· via BenchBoard docs | 89.7% |