Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

Arena WebDev RatingCoding

Official website

Results for 88 models collected from 3 public sources.

#ModelScore

1

Kimi K3Moonshot AI

1,678.5Elo

2

Claude Fable 5Anthropic

1,652.7Elo

3

GPT-5.6 SolOpenAI · Codex-harness mode

1,631.0Elo

4

gpt-5.6-sol-xhigh (codex-harness)OpenAI · Codex-harness mode

1,617.8Elo

5

GLM-5.2Z.ai · Max mode

1,587.1Elo

6

Claude Opus 4.8Anthropic · Thinking mode

1,561.7Elo

7

Claude Opus 4.7Anthropic · Thinking mode

1,558.9Elo

8

Grok 4.5xAI

1,558.2Elo

9

Claude Sonnet 5Anthropic · Thinking mode

1,551.3Elo

10

Claude Opus 4.6Anthropic · Thinking mode

1,542.4Elo

88 models total