Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Domain-Specific Agentic Reasoning on τ³ Banking
Loading...
21.7
Score
Fugu
7.868
11.459
15.05
18.641
Jun 19, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Fugu
2026.06
21.7
Fugu-Ultra
2026.06
20.6
Claude Opus 4.8
2026.06
20.6
GPT-5.5
2026.06
20.6
Gemini 3.1
2026.06
8.4
Feedback
Search any
task
Search any
task