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

v0.1.60.46f2d15f9eca浙ICP备09076226号-7

Back to benchmarks

Terminal-Bench-Science 0.1ReasoningAgents

Results for 12 models collected from 7 public sources.

Ranking Sources

#ModelScore

1

GPT-6 AstraOpenAI

68.1%

2

Claude Opus 5.5Anthropic

63.3%

3

Claude Sonnet 5.5Anthropic

59.9%

4

Gemini 4 ArgonGoogle

57.6%

5

GPT-6.1 SolOpenAI · max

57.0%

6

Claude Fable 5.1Anthropic

52.6%

7

Claude Opus 5Anthropic

30.0%

8

GPT-6 SolOpenAI · max

27.6%

9

Claude Fable 5Anthropic

24.7%

10

GPT-5.6 SolOpenAI

22.4%

12 models total