Mathematical Reasoning on GSM8K (s, rho_b, self-consistency)
0.93s ScoreLlama-3-70B-Instruct
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Llama-3-70B-InstructModel=Llama-3-70B-Instruct2026.06 | 0.93 | 0.41 | 0.24 | 2.5 | 1 | 0.97 | |
| Llama-3-8B-InstructModel=Llama-3-8B-Instruct2026.06 | 0.77 | 0.47 | 0.4 | 2.1 | 1 | 0.87 |