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

DeepSearchQA (F1)Agents

Official website

Results for 19 models collected from 5 public sources.

#ModelScore

1

GPT-5.5OpenAI

95.5%

2

Kimi K3Moonshot AI

95.0%

3

Claude Fable 5Anthropic

94.2%

4

Claude Opus 4.8Anthropic

93.1%

5

Kimi-K2.6Moonshot AI

92.5%

6

Claude Opus 4.6Anthropic

91.3%

7

Hunyuan 3Tencent

91.0%

8

Seed2.1 ProByteDance

90.8%

9

Gemini 3.1 ProGoogle

90.4%

10

DeepSeek-V4-ProDeepSeek

90.4%

19 models total

Benchmark details loading

Back to benchmarks

DeepSearchQA (F1)Agents

Official website

Results for 19 models collected from 5 public sources.

#ModelScore

1

GPT-5.5OpenAI

95.5%

2

Kimi K3Moonshot AI

95.0%

3

Claude Fable 5Anthropic

94.2%

4

Claude Opus 4.8Anthropic

93.1%

5

Kimi-K2.6Moonshot AI

92.5%

6

Claude Opus 4.6Anthropic

91.3%

7

Hunyuan 3Tencent

91.0%

8

Seed2.1 ProByteDance

90.8%

9

Gemini 3.1 ProGoogle

90.4%

10

DeepSeek-V4-ProDeepSeek

90.4%

19 models total