List Maximum on Common Numeracy Benchmarks
98Accuracy (Range $10^2$)
CONE
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.03 | 98 | 95 | 97 | 96 | 95 | |
2026.03 | 97 | 96 | 96 | 95 | 94 | |
2026.03 | 95 | 94 | 92 | 91 | 88 | |
2026.03 | 94 | 63 | 50 | 47 | 42 | |
2026.03 | 17 | 22 | 20 | 18 | 16 |
CONE
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.03 | 98 | 95 | 97 | 96 | 95 | |
2026.03 | 97 | 96 | 96 | 95 | 94 | |
2026.03 | 95 | 94 | 92 | 91 | 88 | |
2026.03 | 94 | 63 | 50 | 47 | 42 | |
2026.03 | 17 | 22 | 20 | 18 | 16 |