Correlation Analysis on Reasoning Benchmark Suite (AIME, GSM8K, MMLU, GPQA)
0.741Pearson r
TRACE
Updated 5d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 0.741 | 0.755 | |
2026.05 | 0.221 | 0.145 | |
2026.05 | 0.207 | 0.244 | |
2026.05 | 0.147 | 0.186 |
TRACE
| Method | Links | ||
|---|---|---|---|
2026.05 | 0.741 | 0.755 | |
2026.05 | 0.221 | 0.145 | |
2026.05 | 0.207 | 0.244 | |
2026.05 | 0.147 | 0.186 |