Cultural norm reasoning on NormAd Europe 1.0 (test)
77.42AccuracyMinistral-3-3B
Evaluation Results
| Method | Links | |
|---|---|---|
| Ministral-3-3BPrompt Language=Source-Language Stories2026.03 | 77.42 | |
| Gemma3-4BPrompt Language=Source-Language Stories2026.03 | 75.37 | |
| Tiny Aya FirePrompt Language=Source-Language Stories2026.03 | 75.02 | |
| SmolLM3-3BPrompt Language=Source-Language Stories2026.03 | 74.4 | |
| Qwen3.5-4BPrompt Language=Source-Language Stories2026.03 | 72.7 | |
| Tiny Aya GlobalPrompt Language=Source-Language Stories2026.03 | 72.27 | |
| Tiny Aya EarthPrompt Language=Source-Language Stories2026.03 | 71.98 | |
| Tiny Aya WaterPrompt Language=Source-Language Stories2026.03 | 71.95 | |
| Qwen3-4BPrompt Language=Source-Language Stories2026.03 | 67.24 |