Skip to content

Benchmark

ClawEval · Pass³ · Version Unspecified

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.00

Score distribution

61%
Mean
60.3%
Median
6.3%
Std dev
56.7%
10th percentile
74.5%
90th percentile
55.8%
Min
55.8%74.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1MiniMax M3General group · 161 tasks · Pass³ · Gemini 3.0 Flash grader· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.5%
2Agnes 2.0 FlashAgnes 2.0 Flash official documentation · general · Pass³ · exact version not stated· Reported by Agnes AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.9%
3GPT 5.4SenseNova 6.7 Flash-Lite official benchmark chart · Pass³ · exact Claw-Eval version and harness not stated· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.3%
4Gemini 3.1 Pro PreviewSenseNova 6.7 Flash-Lite official benchmark chart · Pass³ · exact Claw-Eval version and harness not stated· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.8%
5Step 3.5 FlashSenseNova 6.7 Flash-Lite official benchmark chart · Pass³ · exact Claw-Eval version and harness not stated· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.7%
6GLM 5SenseNova 6.7 Flash-Lite official benchmark chart · Pass³ · exact Claw-Eval version and harness not stated· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.8%

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.