Loading...
Loading...
Tau Bench (Retail)
7
Total Models
63.53
Average Score
28.10 - 82.40
Score Range
1
Max Score Achievable
Top 10 Model Performance
7 models
Models Using This Benchmark(7)
LG(2 models)
62.80%
28.10%
OpenAI(2 models)
gpt-oss-120b
openai
67.80%
gpt-oss-20b
openai
54.80%
Qwen(2 models)
77.50%
71.30%
Anthropic(1 model)
Claude Opus 4.1
anthropic
82.40%