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

v0.1.52.d0cbabc1dc7f浙ICP备09076226号-7

Back to benchmarks

Terminal-Bench 2.1Agents

Results for 30 models collected from 13 public sources.

Ranking Sources

#ModelScore

1

GPT-5.6 SolOpenAI · max mode

88.8%

2

Muse Spark 1.3Meta · max mode

88.8%

3

Kimi K3Moonshot AI

88.3%

4

GLM-5.3Zhipu AI

88.2%

5

Claude Fable 5Anthropic

88.0%

6

DeepSeek-V4-Pro-0813DeepSeek

87.9%

7

GPT-5.6 TerraOpenAI

87.4%

8

Claude Opus 5Anthropic · max mode

86.7%

9

Qwen3.8-MaxAlibaba

86.6%

10

Gemini 3.7 FlashGoogle

85.8%

30 models total

Benchmark details loading

Back to benchmarks

Terminal-Bench 2.1Agents

Results for 30 models collected from 13 public sources.

Ranking Sources

#ModelScore

1

GPT-5.6 SolOpenAI · max mode

88.8%

2

Muse Spark 1.3Meta · max mode

88.8%

3

Kimi K3Moonshot AI

88.3%

4

GLM-5.3Zhipu AI

88.2%

5

Claude Fable 5Anthropic

88.0%

6

DeepSeek-V4-Pro-0813DeepSeek

87.9%

7

GPT-5.6 TerraOpenAI

87.4%

8

Claude Opus 5Anthropic · max mode

86.7%

9

Qwen3.8-MaxAlibaba

86.6%

10

Gemini 3.7 FlashGoogle

85.8%

30 models total