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 Agent Tool HallucinationAgents

Results for 31 models collected from 2 public sources.

#ModelScore

1

Claude Fable 5Anthropic · High mode

1.3%

2

GPT-5.6 SolOpenAI · xHigh mode

1.3%

3

GPT-5.5OpenAI · xHigh mode

1.3%

4

GLM-5.2Z.ai · Max mode

1.3%

5

GPT-5.4OpenAI · High mode

1.3%

6

Grok 4.5xAI

1.3%

7

GLM-5.1Zhipu AI

1.3%

8

Muse Spark 1.1Meta

1.3%

9

Kimi-K2.7-CodeMoonshot AI

1.3%

10

Kimi-K2.6Moonshot AI

1.3%

31 models total

Benchmark details loading

Back to benchmarks

Arena Agent Tool HallucinationAgents

Results for 31 models collected from 2 public sources.

#ModelScore

1

Claude Fable 5Anthropic · High mode

1.3%

2

GPT-5.6 SolOpenAI · xHigh mode

1.3%

3

GPT-5.5OpenAI · xHigh mode

1.3%

4

GLM-5.2Z.ai · Max mode

1.3%

5

GPT-5.4OpenAI · High mode

1.3%

6

Grok 4.5xAI

1.3%

7

GLM-5.1Zhipu AI

1.3%

8

Muse Spark 1.1Meta

1.3%

9

Kimi-K2.7-CodeMoonshot AI

1.3%

10

Kimi-K2.6Moonshot AI

1.3%

31 models total