Scientific Reasoning on ARC-C en
82.81AccuracySFT
Evaluation Results
| Method | Links | |
|---|---|---|
| SFTN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 82.81 | |
| ORPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 82.77 | |
| BaselineN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 82.55 | |
| DPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 82.32 | |
| TLPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 82.29 |