Skip to content

Benchmark

QwenWebDev

Coding benchmarks compare models on programming tasks. Scores are Elo ratings. Higher ratings are better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

1,552
Mean
1,568
Median
16
Std dev
1,536
10th percentile
1,568
90th percentile
1,536
Min
1,5361,568
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.7 MaxQwen3.7-Max release · internal bilingual frontend benchmark · auto-render + multimodal judge · BT/Elo· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.1,568
2Qwen3.7 PlusQwen3.7-Plus release · internal bilingual frontend benchmark · auto-render + multimodal judge · BT/Elo· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.1,536

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.