Tool-use on BFCL, MCP-Atlas, τ²-Bench, and VitaBench Summary
33.4Average Success RateEnvFactory
Evaluation Results
| Method | Links | |
|---|---|---|
| EnvFactoryBackbone=Qwen3-8B, Env. (Data Scale)=85, Tasks (Data Scale)=2,5752026.05 | 33.4 | |
| EnvScalerBackbone=Qwen3-8B, Env. (Data Scale)=191, Tasks (Data Scale)=11,5722026.05 | 32.72 | |
| EnvFactory (SFT)Backbone=Qwen3-8B, Env. (Data Scale)=85, Tasks (Data Scale)=1,6222026.05 | 30.82 | |
| EnvFactoryBackbone=Qwen3-4B, Env. (Data Scale)=85, Tasks (Data Scale)=2,5752026.05 | 30.77 | |
| EnvScalerBackbone=Qwen3-4B, Env. (Data Scale)=191, Tasks (Data Scale)=11,5722026.05 | 29.56 | |
| BaseBackbone=Qwen3-8B, Env. (Data Scale)=–, Tasks (Data Scale)=–2026.05 | 29.23 | |
| AWMBackbone=Qwen3-8B, Env. (Data Scale)=526, Tasks (Data Scale)=3,3152026.05 | 28.65 | |
| EnvFactory (SFT)Backbone=Qwen3-4B, Env. (Data Scale)=85, Tasks (Data Scale)=1,6222026.05 | 27.29 | |
| AWMBackbone=Qwen3-4B, Env. (Data Scale)=526, Tasks (Data Scale)=3,3152026.05 | 25.47 | |
| BaseBackbone=Qwen3-4B, Env. (Data Scale)=–, Tasks (Data Scale)=–2026.05 | 24.09 | |
| EnvFactoryBackbone=Qwen3-1.7B, Env. (Data Scale)=85, Tasks (Data Scale)=2,5752026.05 | 19.74 | |
| EnvFactory (SFT)Backbone=Qwen3-1.7B, Env. (Data Scale)=85, Tasks (Data Scale)=1,6222026.05 | 18.6 | |
| EnvScalerBackbone=Qwen3-1.7B, Env. (Data Scale)=191, Tasks (Data Scale)=11,5722026.05 | 16.51 | |
| BaseBackbone=Qwen3-1.7B, Env. (Data Scale)=–, Tasks (Data Scale)=–2026.05 | 16.27 |