Agent on Tau2 Retail (English)
71.6ScoreHyperCLOVA X 32B Think
Evaluation Results
| Method | Links | |
|---|---|---|
| HyperCLOVA X 32B ThinkUser-simulator=GPT-4.12026.01 | 71.6 | |
| EXAONE 4.0 32BUser-simulator=GPT-4.12026.01 | 59.5 | |
| Qwen3-VL 32B-ThinkingUser-simulator=GPT-4.12026.01 | 57 |