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

v0.1.36.770f52594d07浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

DSBench-HardCodingAgents

DeepSeek's internal benchmark for difficult coding-agent tasks.

Ranking Sources

#ModelScore

1

Claude Opus 4.8Anthropic

71.7%

2

DeepSeek-V4-Flash-0731DeepSeek

59.6%

3

GLM-5.2Zhipu AI

54.5%

4

DeepSeek-V4-ProDeepSeek

31.1%

5

DeepSeek-V4-FlashDeepSeek

25.8%

5 models total