List your company

Science Question Answering on GPQA diamond en

32.32AccuracyBaseline
27.69228.893530.09531.2965Apr 29, 2026

Evaluation results

MethodLinks
BaselineN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.0432.32
TLPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.0431.66
ORPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.0431.19
DPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.0431.09
SFTN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.0427.87