Stateful Interaction on tau2-bench
86.69ScoreQwen3.5-9B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-9BBackbone=Qwen3.5-9B, Quantization Method=BF162026.05 | 86.69 | |
| Mix-QuantBackbone=Qwen3.5-9B, Quantization Method=Mix-Quant2026.05 | 81.89 | |
| Qwen3.5-9B-NVFP4Backbone=Qwen3.5-9B, Quantization Method=NVFP4 W4A42026.05 | 76.26 | |
| Gemma-4-31B-itBackbone=Gemma-4-31B-it, Quantization Method=BF162026.05 | 73.5 | |
| Mix-QuantBackbone=Gemma-4-31B-it, Quantization Method=Mix-Quant2026.05 | 72.84 | |
| Gemma-4-31B-it-NVFP4Backbone=Gemma-4-31B-it, Quantization Method=NVFP4 W4A42026.05 | 70.74 | |
| Gemma-4-26B-A4B-itBackbone=Gemma-4-26B-A4B-it, Quantization Method=BF162026.05 | 64.63 | |
| Mix-QuantBackbone=Gemma-4-26B-A4B-it, Quantization Method=Mix-Quant2026.05 | 60.62 | |
| Gemma-4-26B-A4B-it-NVFP4Backbone=Gemma-4-26B-A4B-it, Quantization Method=NVFP4 W4A42026.05 | 57.31 | |
| Qwen3-8BBackbone=Qwen3-8B, Quantization Method=BF162026.05 | 31.06 | |
| Mix-QuantBackbone=Qwen3-8B, Quantization Method=Mix-Quant2026.05 | 28.86 | |
| Qwen3-8B-NVFP4Backbone=Qwen3-8B, Quantization Method=NVFP4 W4A42026.05 | 27.34 |