Cultural norm reasoning on NormAd West Asia 1.0 (test)
69.53AccuracyQwen3.5-4B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-4BPrompt Language=Source-Language Stories2026.03 | 69.53 | |
| Tiny Aya WaterPrompt Language=Source-Language Stories2026.03 | 69.27 | |
| Tiny Aya FirePrompt Language=Source-Language Stories2026.03 | 68.87 | |
| SmolLM3-3BPrompt Language=Source-Language Stories2026.03 | 68.83 | |
| Tiny Aya GlobalPrompt Language=Source-Language Stories2026.03 | 67.44 | |
| Qwen3-4BPrompt Language=Source-Language Stories2026.03 | 66.47 | |
| Tiny Aya EarthPrompt Language=Source-Language Stories2026.03 | 66.35 | |
| Gemma3-4BPrompt Language=Source-Language Stories2026.03 | 63.11 | |
| Ministral-3-3BPrompt Language=Source-Language Stories2026.03 | 53.32 |