Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.51.9d125332c988浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

QwenSWEBench V2Coding

Qwen internal software-engineering benchmark evaluated with Claude Code; avg@3, 8-hour timeout, 64K maximum tokens, temperature 1.0, and a 1M context window.

Ranking Sources

#ModelScore

1

Qwen3.8-MaxAlibaba · 0902

70.0%

2

Claude Opus 5Anthropic

68.0%

3

Claude Fable 5Anthropic

67.1%

3 models total