Reasoning on BBEH (ACC., LEN.)
75.8AccuracyCoT2-Meta
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoT2-MetaStrategy=Ours (CoT2-Meta), Inference Budget=C=162026.03 | 75.8 | — | |
| ReST-MCTS*Strategy=ReST-MCTS*, Inference Budget=C=162026.03 | 73.8 | — | |
| Vanilla ToTStrategy=Vanilla ToT, Inference Budget=C=162026.03 | 71.2 | — | |
| Best-of-16Strategy=Best-of-16, Inference Budget=C=162026.03 | 68.9 | — | |
| Greedy CoTStrategy=Greedy CoT, Inference Budget=C=162026.03 | 65.4 | — | |
| DDPOModel=Qwen3-14b, theta=0.22026.03 | 21.2 | 6,185 | |
| GRPOModel=Qwen3-14b2026.03 | 21.03 | 6,851 |