Reasoning on ZebraLogic (Avg@1)
44.5Avg Accuracy@1General-Reasoner-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| General-Reasoner-14BModel Category=Frontier Models2026.04 | 44.5 | |
| TEMPOBase Model=OLMO3-7B-Base2026.04 | 35.1 | |
| TEMPOBase Model=Qwen3-8B-Base2026.04 | 33.9 | |
| TTRLBase Model=Qwen3-8B-Base2026.04 | 31.7 | |
| MiMo-Zero-RL-7BModel Category=Frontier Models2026.04 | 30.3 | |
| EMPOBase Model=Qwen3-8B-Base2026.04 | 26.3 | |
| General-Reasoner-7BModel Category=Frontier Models2026.04 | 25.9 | |
| Olmo-3-7B-RL-Zero-GeneralModel Category=Frontier Models2026.04 | 25.7 | |
| Zero-RL (PPO)Base Model=Qwen3-8B-Base2026.04 | 25.7 | |
| EMPOBase Model=OLMO3-7B-Base2026.04 | 23.5 | |
| Zero-RL (PPO)Base Model=OLMO3-7B-Base2026.04 | 22.2 | |
| TTRLBase Model=OLMO3-7B-Base2026.04 | 22.2 |