Multi-task Scoring on OmniScore (Evaluation Set)
0.99Average MAGemini-3.1-Flash-Lite
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3.1-Flash-LiteContext Size=65k2026.04 | 0.99 | |
| mBERT2026.04 | 0.85 | |
| Ettin-150MParams=150M2026.04 | 0.84 | |
| DeBERTa-v3Params=86M, Context Size=5122026.04 | 0.81 | |
| mxbai-largeParams=335M, Context Size=1K2026.04 | 0.78 |