Skip to content

Benchmark

Claw-Eval v1.1 · Multimodal (101) · Pass³

Scores are percentages. Higher is better.

Models and systems measured
11
Scores recorded
11
Sources
1
IQ weight
0.45

Score distribution

19.3%
Mean
18.8%
Median
4.4%
Std dev
14.8%
10th percentile
24.8%
90th percentile
13.9%
Min
13.9%25.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.45 for chat models, measured over 10 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 5.4Claw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs25.7%
2Claude Opus 4.6Claw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs24.8%
3Claude Sonnet 4.6Claw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs23.8%
4MiMo V2.5Claw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs23.8%
5Qwen3.5 397B A17BClaw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs20.8%
6Kimi K2.6Claw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs18.8%
7Gemini 3.1 Pro PreviewClaw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs15.8%
8MiMo V2 OmniClaw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs15.8%
9Gemini 3 FlashClaw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs14.8%
10Kimi K2.5Claw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs14.8%

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 5V TurboClaw-Eval v1.1 · multimodal · 101 tasks · N=3 · grader: Gemini 3 Flash· Reported by Claw-Eval· via BenchBoard docs13.9%

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.