Evaluation on TAXI1500 (test)
64.9SLFRMACRO
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MACROModel=Gemma3-4B, Language=hi, Evaluation Protocol=Zero-shot2026.05 | 64.9 | 5.99 | 71.9 | |
| DG-CFModel=Gemma3-4B, Language=hi, Evaluation Protocol=Zero-shot2026.05 | 64 | 5.92 | 63.5 | |
| MACROModel=Gemma3-4B, Language=th, Evaluation Protocol=Zero-shot2026.05 | 63.1 | 8.57 | 63.6 | |
| MACROModel=Gemma3-4B, Language=es, Evaluation Protocol=Zero-shot2026.05 | 62.2 | 19 | 70.2 | |
| MACROModel=Qwen3-4B, Language=th, Evaluation Protocol=Zero-shot2026.05 | 62.2 | 10 | 68.8 | |
| DG-CFModel=Gemma3-4B, Language=es, Evaluation Protocol=Zero-shot2026.05 | 59.5 | 19.33 | 65.8 | |
| DG-CFModel=Gemma3-4B, Language=th, Evaluation Protocol=Zero-shot2026.05 | 59.5 | 8.94 | 57.4 | |
| DG-CFModel=Qwen3-4B, Language=th, Evaluation Protocol=Zero-shot2026.05 | 59.5 | 8.97 | 61.9 | |
| MACROModel=Qwen3-4B, Language=es, Evaluation Protocol=Zero-shot2026.05 | 58.6 | 21.93 | 74.3 | |
| DG-CFModel=Qwen3-4B, Language=es, Evaluation Protocol=Zero-shot2026.05 | 50.5 | 19.05 | 66.5 | |
| DG-CFModel=Qwen3-4B, Language=hi, Evaluation Protocol=Zero-shot2026.05 | 38.7 | 6.41 | 67.6 | |
| MACROModel=Qwen3-4B, Language=hi, Evaluation Protocol=Zero-shot2026.05 | 27 | 6.94 | 79.3 |