Skip to content

Benchmark

QwenSWEBench

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

Models measured
6
Scores recorded
8
Sources
2
IQ weight
1.02

Score distribution

78.3%
Mean
80.7%
Median
6.7%
Std dev
73.5%
10th percentile
84%
90th percentile
63.4%
Min
63.4%86.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.02 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
1Claude Fable 5Qwen内部基准:Claude Code · avg@3 · 8h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.3%
2Claude Opus 4.8Qwen内部基准:Claude Code · avg@3 · 8h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84%
3Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.7%
4Qwen3.8 MaxQwen内部基准:Claude Code · avg@3 · 8h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.7%
5Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79%
6Qwen 3.8 27BQwen3.8-27B model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.79%
7GPT-5.6 SolQwen内部基准:Claude Code · avg@3 · 8h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.5%
8Qwen3.7 MaxQwen内部基准:Claude Code · avg@3 · 8h · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.4%

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