| Benchmark | Model | Rank | Results |
|---|---|---|---|
| logic-puzzle-solving-on-zebralogic | OLMO3-7B-Base (TEMPO) | #12 | Accuracy: 35.1 |
| mathematical-reasoning-on-aime-2026 | Qwen3-14B-Base (TEMPO) | #49 | Accuracy: 38.8 |
| mathematical-reasoning-on-aime24 | Qwen3-14B-Base (TEMPO) | #58 | Acc: 65.8 |
| mathematical-reasoning-on-aime-2025 | Qwen3-14B-Base (TEMPO) | #89 | Accuracy: 44.6 |