Tool-use Agent Evaluation on τ-bench retail domain (All 115 tasks)
43.9Pass@1POLCA
Evaluation Results
| Method | Links | |
|---|---|---|
| POLCA2026.03 | 43.9 | |
| GEPA2026.03 | 42.9 | |
| OpenEvolve2026.03 | 41.8 | |
| Base Prompt2026.03 | 38.9 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| POLCA2026.03 | 43.9 | |
| GEPA2026.03 | 42.9 | |
| OpenEvolve2026.03 | 41.8 | |
| Base Prompt2026.03 | 38.9 |