Multilingual Multiple-Choice Reasoning on Global PIQA 116 languages 1.0 (test)
79.31AccuracyQwen3.5-4B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-4Bdecoding=greedy, parameters=4B2026.03 | 79.31 | |
| Qwen3-4Bdecoding=greedy, parameters=4B2026.03 | 74.6 | |
| Gemma3-4Bdecoding=greedy, parameters=4B2026.03 | 70.8 | |
| Ministral-3-3Bdecoding=greedy, parameters=3B2026.03 | 70.7 | |
| Tiny Aya Globaldecoding=greedy2026.03 | 68.3 | |
| SmolLM3-3Bdecoding=greedy, parameters=3B2026.03 | 63.2 |