Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn Financial Advisory Dialogue on FAR-Trans 50 persona-expressive investors (test)
Loading...
66.5
Turn 3 Pairwise Win Rate
Matched Persona (Fund2Persona)
16.06
29.155
42.25
55.345
Jun 29, 2026
Turn 3 Pairwise Win Rate
Turn 5 Pairwise Win Rate
Preference Fit Rubric Score
Practical Usefulness Rubric Score
Updated 25d ago
Evaluation Results
Method
Method
Links
Turn 3 Pairwise Win Rate
Turn 5 Pairwise Win Rate
Preference Fit Rubric Score
Practical Usefulness Rubric Score
Matched Persona (Fund2Persona)
Generator=Gemini 3.1 F...
2026.06
66.5
78
3.6
3.26
Generic LLM
Generator=Gemini 3.1 F...
2026.06
49
31
3.34
3.14
Mismatched Persona
Generator=Gemini 3.1 F...
2026.06
18
13
2.46
2.4
Feedback
Search any
task
Search any
task