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 Text RatingReasoning

Official website

Results for 354 models collected from 3 public sources.

#ModelScore

1

Claude Fable 5Anthropic

1,508.5Elo

2

Claude Opus 4.6Anthropic · Thinking mode

1,503.8Elo

3

Claude Opus 4.7Anthropic · Thinking mode

1,502.9Elo

4

Muse Spark 1.1Meta

1,493.1Elo

5

Muse SparkMeta

1,487.6Elo

6

GPT-5.6 SolOpenAI · xHigh mode

1,486.3Elo

7

Gemini 3.1 ProGoogle · Preview mode

1,485.8Elo

8

Gemini 3 ProGoogle

1,485.8Elo

9

Kimi K3Moonshot AI

1,485.6Elo

10

Gemini 3.1 Pro PreviewGoogle · Preview mode

1,485.4Elo

354 models total

Benchmark details loading

Back to benchmarks

Arena Text RatingReasoning

Official website

Results for 354 models collected from 3 public sources.

#ModelScore

1

Claude Fable 5Anthropic

1,508.5Elo

2

Claude Opus 4.6Anthropic · Thinking mode

1,503.8Elo

3

Claude Opus 4.7Anthropic · Thinking mode

1,502.9Elo

4

Muse Spark 1.1Meta

1,493.1Elo

5

Muse SparkMeta

1,487.6Elo

6

GPT-5.6 SolOpenAI · xHigh mode

1,486.3Elo

7

Gemini 3.1 ProGoogle · Preview mode

1,485.8Elo

8

Gemini 3 ProGoogle

1,485.8Elo

9

Kimi K3Moonshot AI

1,485.6Elo

10

Gemini 3.1 Pro PreviewGoogle · Preview mode

1,485.4Elo

354 models total