the ai forger
Models
Organizations
Providers
Benchmarks
Compare

TAU-bench Retail

agents
text
About

TAU-bench Retail benchmark

Evaluation Stats
Total Models15
Organizations3
Verified Results0
Self-Reported15
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

15 models
Top Score
81.4%
Average Score
64.2%
High Performers (80%+)
3

Top Organizations

#1Anthropic
6 models
70.6%
#2DeepSeek
1 model
63.9%
#3OpenAI
8 models
59.4%
Leaderboard
Top 15 models ranked by performance
1
81.4%
Raw: 0.814
Self-reported
2
81.2%
Raw: 0.812
Self-reported
3
80.5%
Raw: 0.805
Self-reported
4
71.8%
Raw: 0.718
Self-reported
5
70.8%
Raw: 0.708
Self-reported
6
69.2%
Raw: 0.692
Self-reported
7
68.4%
Raw: 0.684
Self-reported
8
68.0%
Raw: 0.68
Self-reported
9
63.9%
Raw: 0.639
Self-reported
10
60.4%
Raw: 0.604
Self-reported
11
60.3%
Raw: 0.603
Self-reported
12
57.6%
Raw: 0.576
Self-reported
13
55.8%
Raw: 0.558
Self-reported
14
51.0%
Raw: 0.51
Self-reported
15
22.6%
Raw: 0.226
Self-reported