Multiple Choice Question Answering on MedMCQA i.d.
82.66AccuracyStackedGen
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| StackedGen2026.07 | 82.66 | 2.21 | 59.06 | 30.91 | 11.56 | |
| WALLA Icalibration=calibrated2026.07 | 82.53 | 10.56 | 65.98 | 38.92 | 11.69 | |
| RouteLLM2026.07 | 81.7 | 3.62 | 55.64 | 27.67 | 12.82 | |
| WALLA I2026.07 | 81.17 | 7.59 | 55.26 | 24.17 | 14.86 | |
| NIRTRouter2026.07 | 81.15 | 6.99 | 55.64 | 27.67 | 14.56 | |
| WALLA II2026.07 | 81 | 7.85 | 55.3 | 21.95 | 15.36 | |
| WALLA Ipooling=log-pool2026.07 | 80.32 | 2.07 | 55.01 | 23.15 | 14.58 | |
| Aloe2026.07 | 79.77 | 3.18 | 59.49 | 14.42 | 15.77 | |
| PackLLM2026.07 | 79 | 9.93 | 50.77 | 8.85 | 18.93 | |
| Llama3.12026.07 | 78.97 | 2.64 | 51.56 | 4.47 | 15.97 | |
| RouterDC2026.07 | 78.95 | 8.77 | 55.65 | 27.65 | 18.35 | |
| UniformAvg2026.07 | 76.45 | 8.1 | — | 0 | 21.05 | |
| SelfCertainty2026.07 | 74.42 | 4.58 | 79.78 | 43.61 | 22.08 | |
| Gemma22026.07 | 62.9 | 25.28 | 64.99 | 5.93 | 47.28 | |
| BioMistral2026.07 | 47.47 | 17.1 | 37.71 | -24.82 | 56.24 |