Mathematical Problem Solving on MATH 8-shot
73.89AccuracyERNIE 5.0-Base
Evaluation Results
| Method | Links | |
|---|---|---|
| ERNIE 5.0-BaseNumber of shots=8-shot, Evaluation Protocol=Chain of Thought (CoT)2026.02 | 73.89 | |
| Kimi K2-BaseNumber of shots=8-shot, Evaluation Protocol=Chain of Thought (CoT)2026.02 | 65.9 | |
| DS V3.2-Exp-BaseNumber of shots=8-shot, Evaluation Protocol=Chain of Thought (CoT)2026.02 | 65.7 |