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

Mathematical Reasoning (HS/FA Metrics) on GSM8K (test)

59.6HS

NA-SFT

6.14420.02233.947.778May 28, 2024Sep 8, 2024Dec 20, 2024Apr 2, 2025Jul 14, 2025Oct 25, 2025Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.05
59.67.2
2024.05
57.221.93
2024.05
56.724
2024.05
55.334.6
2024.05
55.334.6
2024.05
53.86.6
2024.05
52.322.1
2024.05
51.46.7
2024.05
5117.67
2024.05
49.619.1
2024.05
49.27.1
2024.05
48.921.5
2024.05
48.0717.13
2024.05
487.4
2024.05
4823
2024.05
47.3711.57
2024.05
46.924.3
2024.05
46.924.3
2024.05
46.4717.93
2024.05
46.122.8
2024.05
46.122.8
2024.05
43.423.4
2024.05
43.423.4
2024.05
41.18.9
2024.05
41.18.9
2024.05
36.817.9
2024.05
36.728
2024.05
36.728
2024.05
36.1716.1
2024.05
352.4
2026.02
32.274.9
2026.02
27.664.7
2026.02
27.664.7
2026.02
27.377
2026.02
27.390.7
2026.02
23.375
2026.02
21.190
2026.02
20.668.2
2026.02
20.668.2
2026.02
2090.8
2026.02
18.565.3
2026.02
18.565.3
2026.02
18.390.2
2026.02
17.667.6
2026.02
17.667.6
2026.02
17.390.5
2026.02
17.286.4
2026.02
17.290.8
2026.02
16.857.1
2026.02
16.857.1
2026.02
16.168.2
2026.02
16.168.2
2026.02
14.869.5
2026.02
14.869.5
2026.02
13.781.7
2026.02
12.882.5
2026.02
11.389.7
2026.02
1080.2
2026.02
9.580.4
2026.02
8.968.5
2026.02
8.968.5
2026.02
8.277.1