Science Question Answering on GPQA en
32.83AccuracyBaseline
Evaluation Results
| Method | Links | |
|---|---|---|
| BaselineN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 32.83 | |
| ORPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 31.52 | |
| DPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 31.1 | |
| TLPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 30.66 | |
| SFTN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 28.24 |