Skip to content

Benchmark

Claw-Eval

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
24
Scores recorded
24
Sources
2
IQ weight
0.28

Score distribution

61.1%
Mean
62.7%
Median
13%
Std dev
52.8%
10th percentile
74.5%
90th percentile
6.8%
Min
6.8%80.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.28 for chat models, measured over 24 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
80.9%
2LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.3%
3GLM 5V Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75%
4MiniMax M3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
74.5%
5Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.5%
6Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.2%
7MiMo V2.5 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
64%
8Ring 2.6 1T· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim63.8%
9MiMo V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
63.2%
10LFM2.5 2.6B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.9%
11GLM 5.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim62.7%
12Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.7%
13MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.5%
14Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.6%
15Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.7%
16DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim58.4%
17openPangu 2.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim58.2%
18DeepSeek V4 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim57.8%
19Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim57.8%
20MiMo V2 Omni· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.8%
21Kimi K2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim52.8%
22Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%
23MiniMax M2.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim49.7%
24Nemotron 3 Super 120B A12B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim6.8%

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