Skip to content

Benchmark

WildClawBench · Overall

Scores are percentages. Higher is better.

Models and systems measured
34
Scores recorded
35
Sources
1
IQ weight
1.25

Score distribution

45.4%
Mean
46.9%
Median
11.5%
Std dev
30.8%
10th percentile
62%
90th percentile
19.3%
Min
19.3%67.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.25 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 systemScore
1GPT-5.6 SolOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs67.2%
2Claude Opus 4.8OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs64.7%
3Claude Opus 4.7OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs62.2%
4Claude Fable 5OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs62%
5GPT 5.5OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs58.2%
6Grok 4.5OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs57.5%
7Qwen3.8 MaxOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs56.2%
8Muse Spark 1.1OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs54.8%
9Kimi K3OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs54.5%
10GLM 5.2OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs54.2%
11Claude Opus 4.6OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs51.6%
12GPT 5.4OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs50.3%
13Hy3 (Deep Infra)OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs49.7%
14GLM 5.1OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs48.2%
15Qwen 3.8 27BOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs48%
16Muse Glimmer 30Bhigh reasoning· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.47.6%
17Muse Glimmer 30BOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs47.6%
18Kimi K2.7 CodeOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs46.9%
19DeepSeek V4 Pro 0813OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs43.7%
20Qwen3.6 27BOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs43.2%
21MiMo V2.5 ProOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs43%
22GLM 5OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs42.6%
23Gemini 3.1 Pro PreviewOpenClaw · full 60-task suite · low-effort· Reported by WildClawBench / InternLM· via BenchBoard docs40.8%
24MiMo V2 ProOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs40.2%
25Gemma 4 31B ITOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs37.6%
26Qwen3.5 397B A17BOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs34.5%
27DeepSeek V3.2OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs34%
28MiniMax M2.7OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs33.8%
29Kimi K2.5OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs30.8%
30MiMo V2 FlashOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs30.8%
31MiniMax M2.5OpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs27.1%
32Step 3.5 FlashOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs26.7%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
GLM 5 TurboOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs33.9%
Grok 4.20 BetaOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs19.3%
Intern-S2 Preview 397BOpenClaw · full 60-task suite· Reported by WildClawBench / InternLM· via BenchBoard docs44.7%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.