Accuracy, Time, and Token Evaluation on MedQA (Medical Reasoning)
79.3AccuracyRecursiveMAS
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RecursiveMASRecursion Round=r=3, Setting=Scaled2026.04 | 79.3 | 1,912 | 1,056 | |
| RecursiveMASRecursion Round=r=2, Setting=Scaled2026.04 | 78.3 | 1,664 | 1,008 | |
| RecursiveMASRecursion Round=r=1, Setting=Scaled2026.04 | 78.2 | 1,348 | 964 | |
| Recursive-TextMASRecursion Round=r=3, Setting=Scaled2026.04 | 77.1 | 3,922 | 3,731 | |
| Recursive-TextMASRecursion Round=r=1, Setting=Scaled2026.04 | 76.1 | 1,522 | 1,427 | |
| Recursive-TextMASRecursion Round=r=2, Setting=Scaled2026.04 | 76.1 | 2,745 | 2,609 | |
| RecursiveMASRecursion Round=r=3, Setting=Light2026.04 | 31.7 | 1,704 | 1,378 | |
| RecursiveMASRecursion Round=r=2, Setting=Light2026.04 | 31.2 | 1,427 | 1,383 | |
| RecursiveMASRecursion Round=r=1, Setting=Light2026.04 | 30.3 | 1,194 | 1,369 | |
| Recursive-TextMASRecursion Round=r=1, Setting=Light2026.04 | 29 | 1,555 | 2,382 | |
| Recursive-TextMASRecursion Round=r=3, Setting=Light2026.04 | 28.5 | 4,684 | 6,307 | |
| Recursive-TextMASRecursion Round=r=2, Setting=Light2026.04 | 28.3 | 3,097 | 4,436 |