Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

TauBench V3 (Banking)Agents

Results for 7 models collected from 1 public source.

#ModelScore

1

DeepSeek-V4-FlashDeepSeek

26.7%

2

DeepSeek-V4-ProDeepSeek

25.9%

3

Kimi-K2.6Moonshot AI

23.1%

4

Nemotron-3-UltraNVIDIA

22.6%

5

Qwen3.5-397B-A17BAlibaba

20.9%

6

MiniMax M2.7MiniMax

14.6%

7

GLM-5.1Zhipu AI

12.8%

7 models total