Skip to content

Benchmark

QwenQoderBench

Scores are percentages. Higher is better.

Models measured
5
Scores recorded
6
Sources
2
IQ weight
0.57

Score distribution

55.5%
Mean
58.4%
Median
8.9%
Std dev
53.8%
10th percentile
63.1%
90th percentile
36.8%
Min
36.8%63.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.57 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5Qwen内部基准:Claude Code · avg@5 · 6h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.1%
2Claude Opus 4.8Qwen内部基准:Claude Code · avg@5 · 6h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62.7%
3Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.4%
4Qwen3.8 MaxQwen内部基准:Claude Code · avg@5 · 6h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.4%
5GPT-5.6 SolQwen内部基准:Claude Code · avg@5 · 6h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53.8%
6Qwen3.7 MaxQwen内部基准:Claude Code · avg@5 · 6h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.8%

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. · Data by LLM Stats