Mathematical Reasoning on Minerva Math (val)
43.34AccuracyGenAC
Evaluation results
| Method | Links | |
|---|---|---|
| GenACAlgorithm=GenAC, Base Model=Qwen3-8B-Base, Sampled generations=16, RL Setup=Zero RL2026.04 | 43.34 | |
| RLOOAlgorithm=RLOO, Base Model=Qwen3-8B-Base, Sampled generations=16, RL Setup=Zero RL2026.04 | 43.22 | |
| VC-PPOAlgorithm=VC-PPO, Base Model=Qwen3-8B-Base, Sampled generations=16, RL Setup=Zero RL2026.04 | 43.02 | |
| GRPOAlgorithm=GRPO, Base Model=Qwen3-8B-Base, Sampled generations=16, RL Setup=Zero RL2026.04 | 42.12 |