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

v0.1.53.364ac010a008浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

DeepSWECoding

Results for 18 models collected from 7 public sources.

Ranking Sources

#ModelScore

1

GPT-5.6 SolOpenAI

73.0%

2

Claude Fable 5Anthropic

70.0%

3

70.0%

4

Kimi K3Moonshot AI

67.5%

5

DeepSeek-V4-Pro-0813DeepSeek

62.7%

6

DeepSeek-V4-Flash-Vision-ExpDeepSeek

59.3%

7

Claude Opus 4.8Anthropic

59.0%

8

DeepSeek-V4-Flash-0731DeepSeek

54.4%

9

GLM-5.2Zhipu AI

46.2%

10

Seed2.1 ProByteDance

32.7%

18 models total