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

Math Reasoning on MathBench EN

50.6Score

InternLM2-Chat-20B-SFT

5.98417.56729.1540.733Mar 26, 2024Jul 25, 2024Nov 23, 2024Mar 25, 2025Jul 24, 2025Nov 22, 2025Mar 24, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2024.03
50.6
2026.03
49.8
2024.03
48.5
2024.03
44.3
2026.03
43.6
2026.03
43.4
2026.03
43
2024.03
42.5
2024.03
42.3
2024.03
40.6
2024.03
40.1
2026.03
39.7
2026.03
39.7
2026.03
39.7
2026.03
36.9
2026.03
36.4
2026.03
35.9
2026.03
35.9
2026.03
35.5
2026.03
35.3
2026.03
33.4
2026.03
32
2026.03
31.4
2026.03
30.5
2026.03
30.4
2024.03
29.1
2024.03
29
2024.03
28.3
2024.03
21.7
2024.03
17.8
2024.03
15.7
2024.03
7.7