Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Benchmark details loading
Back to benchmarks
TauBench V3 (Banking)
Agents
Share
Results for 17 models collected from 4 public sources.
Ranking
Sources
#
Model
Score
1
Kimi K3
Moonshot AI
33.4
%
2
GPT-5.6 Sol
OpenAI
33.0
%
3
GPT-5.5
OpenAI
31.3
%
4
Claude Opus 4.8
Anthropic
27.6
%
5
GLM-5.2
Zhipu AI
26.8
%
6
Claude Fable 5
Anthropic
26.8
%
7
DeepSeek-V4-Flash
DeepSeek
26.7
%
8
DeepSeek-V4-Pro
DeepSeek
25.9
%
9
Muse Glimmer 30B
Meta
23.5
%
10
Kimi-K2.6
Moonshot AI
23.1
%
17 models total
1
2
