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

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

ProgramBenchCoding

Official website

200 instances, Claude-Code 2.1.156, reasoning_effort=max, 400K context

#ModelScore

1

Kimi K3Moonshot AI

77.8%

2

GPT-5.6 SolOpenAI

77.6%

3

Claude Fable 5Anthropic

76.8%

4

Claude Opus 4.8Anthropic

71.9%

5

70.8%

6

GLM-5.2Zhipu AI

63.7%

7

Kimi-K2.7-CodeMoonshot AI

53.6%

8

Claude Opus 4.7Anthropic

52.1%

9

GLM-5.1Zhipu AI

50.9%

10

Seed2.1 ProByteDance

50.3%

14 models total