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

Zero-shot Reasoning on MathQA

28.4Accuracy

Llama2-7B

1.9848.84215.722.558Feb 16, 2026Feb 23, 2026Mar 3, 2026Mar 10, 2026Mar 18, 2026Mar 25, 2026Apr 2, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.02
28.4
2026.04
27
2026.02
26.2
2026.02
23.6
2026.04
23
2026.04
23
2026.02
22.7
2026.02
22.1
2026.02
22
2026.04
22
2026.04
22
2026.02
21.3
2026.04
21
2026.04
21
2026.04
21
2026.04
20
2026.04
18
2026.04
17
2026.04
15
2026.04
12
2026.04
8
2026.04
5
2026.04
5
2026.04
4
2026.04
3
2026.04
3