Skip to content

Benchmark

ResearchClawBench

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
7
Sources
2
IQ weight
0.52

Score distribution

17%
Mean
17.1%
Median
2%
Std dev
14.2%
10th percentile
18.2%
90th percentile
14%
Min
14%20.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.52 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GLM 5.2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim20.7%
2GLM 5.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim18.2%
3Kimi K2.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim18%
4DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim17.1%
5MiMo V2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
16.9%
6Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim14.2%
7Kimi K2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim14%

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats