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

Math on GSM8K

0.988Accuracy

BERT-Judge

0.7925840.8433170.894050.944783Aug 28, 2025Oct 5, 2025Nov 12, 2025Dec 20, 2025Jan 27, 2026Mar 6, 2026Apr 13, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
0.988
2026.04
0.972
2026.03
0.971
2026.04
0.965
2026.03
0.964
2026.03
0.958
2026.04
0.958
2026.04
0.953
2026.04
0.952
2026.04
0.952
2026.04
0.952
2025.08
0.95
2026.04
0.95
2026.04
0.95
2026.04
0.95
2026.04
0.948
2026.04
0.948
2026.03
0.945
2026.04
0.945
2026.04
0.944
2026.04
0.943
2026.04
0.942
2026.04
0.94
2026.04
0.94
2026.04
0.94
2026.04
0.935
2026.04
0.935
2025.08
0.933
2026.04
0.932
2026.04
0.93
2026.04
0.93
2026.04
0.927
2026.04
0.925
2026.04
0.9249
2026.04
0.922
2025.10
0.915
2026.04
0.915
2026.04
0.9136
2026.04
0.91
2026.04
0.91
2026.04
0.907
2026.04
0.907
2026.04
0.905
2026.04
0.903
2026.01
0.901
2025.08
0.9
2026.03
0.8986
2026.01
0.898
2026.01
0.897
2026.04
0.897
2026.01
0.893
2026.04
0.892
2026.01
0.8908
2026.01
0.89
2026.04
0.89
2025.08
0.889
2025.08
0.888
2025.10
0.887
2026.04
0.887
2026.04
0.8848
2026.01
0.8832
2026.01
0.8832
2025.10
0.882
2026.03
0.881
2026.01
0.878
2026.01
0.8757
2025.10
0.873
2026.02
0.873
2025.10
0.87
2026.01
0.866
2026.03
0.865
2025.10
0.864
2026.04
0.8613
2026.01
0.861
2026.01
0.86
2026.03
0.858
2026.03
0.858
2025.10
0.858
2026.03
0.855
2026.03
0.854
2026.02
0.854
2025.10
0.853
2026.04
0.853
2025.08
0.852
2026.03
0.851
2025.12
0.8491
2026.03
0.8489
2026.03
0.8438
2026.03
0.8398
2026.03
0.8375
2026.03
0.836
2026.03
0.8352
2026.01
0.835
2026.04
0.8324
2026.03
0.832
2026.03
0.8203
2025.12
0.8196
2025.10
0.819
2026.03
0.8079
2026.03
0.8001
Showing 100 of 206 rows