Knowledge & Reasoning Evaluation on ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT (test)
51.27Average ScoreTucano2-qwen-3.7B-Think
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Tucano2-qwen-3.7B-Thinkvariant=Think2026.03 | 51.27 | 54.07 | 31.67 | |
| SmolLM3-3B2026.03 | 48.58 | 46.28 | 64.67 | |
| Qwen3-4B2026.03 | 46.35 | 40.97 | 84 | |
| Qwen3-1.7B2026.03 | 36.54 | 32 | 68.33 | |
| Tucano2-qwen-1.5B-Thinkvariant=Think2026.03 | 27.54 | 26.67 | 33.67 | |
| Qwen3-0.6B2026.03 | 24.11 | 19.22 | 58.33 | |
| Tucano2-qwen-0.5B-Thinkvariant=Think2026.03 | 14.41 | 12.52 | 27.67 |