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

Multi-task evaluation on Average GSM8K, HumanEval, ARC-c

60.77Accuracy

ReMix

8.35421.96235.5749.178Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
60.77
2026.03
57.95
2026.03
57.43
2026.03
56.61
2026.03
56.36
2026.03
55.1
2026.03
51.66
2026.03
34.89
2026.03
29.09
2026.03
21.02
2026.03
18.22
2026.03
13.41
2026.03
10.37