Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multiple-choice Question Answering on NaturalBench

32.5Group Accuracy

Llama-90B

13.46818.40923.3528.291Jun 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
32.5
2026.06
28.7
2026.06
27.8
2026.06
27.6
2026.06
24.4
2026.06
20.3
2026.06
14.7
2026.06
14.2