STEM Reasoning on GPQA-Diamond 5-shot
57.3Accuracy
ERNIE 5.0-Base
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 57.3 | |
2026.02 | 53.01 | |
2026.02 | 48.1 | |
2025.12 | 44.95 | |
2025.12 | 41.41 | |
2025.12 | 38.38 | |
2025.12 | 35.86 | |
2025.12 | 33.84 | |
2025.12 | 27.1 | |
2025.12 | 25.25 |