Benchmark
WildClawBench · Pure-text (34 tasks)
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 34
- Scores recorded
- 34
- Sources
- 1
- IQ weight
- 1.81
Score distribution
- 49.4%
- Mean
- 51.7%
- Median
- 9.8%
- Std dev
- 36%
- 10th percentile
- 62.7%
- 90th percentile
- 28.1%
- Min
This benchmark has a weight of 1.81 for chat models, measured over 15 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 | GPT-5.6 SolOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 65.6% |
| 2 | Claude Opus 4.7OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 65% |
| 3 | Claude Opus 4.8OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 64.3% |
| 4 | Kimi K3OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 62.7% |
| 5 | Grok 4.5OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 59.2% |
| 6 | GPT 5.4OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 58% |
| 7 | Claude Fable 5OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 57% |
| 8 | GLM 5.2OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 56.7% |
| 9 | Muse Spark 1.1OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 55.7% |
| 10 | Hy3 (Deep Infra)OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 54.8% |
| 11 | Qwen 3.8 27BOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 54.8% |
| 12 | Claude Opus 4.6OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 54.6% |
| 13 | GPT 5.5OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 54.5% |
| 14 | GLM 5.1OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 53.9% |
| 15 | Qwen3.8 MaxOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 53.7% |
| 16 | GLM 5OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 51.7% |
| 17 | DeepSeek V4 Pro 0813OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 51.4% |
| 18 | Kimi K2.7 CodeOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 50.9% |
| 19 | Muse Glimmer 30BOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 48.4% |
| 20 | MiMo V2 ProOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 48.2% |
| 21 | MiMo V2.5 ProOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 48.1% |
| 22 | Qwen3.6 27BOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 47% |
| 23 | MiniMax M2.7OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 44.9% |
| 24 | Qwen3.5 397B A17BOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 42.6% |
| 25 | DeepSeek V3.2OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 40.1% |
| 26 | Gemma 4 31B ITOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 39.8% |
| 27 | Gemini 3.1 Pro PreviewOpenClaw · pure-text split · 34 tasks · low-effort· Reported by WildClawBench / InternLM· via BenchBoard docs | 38.7% |
| 28 | Step 3.5 FlashOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 37.4% |
| 29 | Kimi K2.5OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 36% |
| 30 | MiniMax M2.5OpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 35.3% |
| 31 | MiMo V2 FlashOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 28.1% |
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 |
|---|---|
| GLM 5 TurboOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 41% |
| Grok 4.20 BetaOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 28.4% |
| Intern-S2 Preview 397BOpenClaw · pure-text split · 34 tasks· Reported by WildClawBench / InternLM· via BenchBoard docs | 52.7% |