Skip to content

Benchmark

ZClawBench

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

57%
Mean
57.6%
Median
4.6%
Std dev
52.6%
10th percentile
64.3%
90th percentile
52.6%
Min
52.6%64.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.3%
2GLM 5V Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.6%
3Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.4%
4Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.6%

Data credits: Data by LLM Stats