Reasoning on BBH en
56.52AccuracySFT
Evaluation results
| Method | Links | |
|---|---|---|
| SFTN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 56.52 | |
| BaselineN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 50.06 | |
| ORPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 48.93 | |
| DPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 48.66 | |
| TLPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 46.97 |