Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (AvgMath/Avg Scores)
Loading...
90.45
GSM8K Score
Equal
87.2156
88.0553
88.895
89.7347
Jul 1, 2026
GSM8K Score
AvgMath Score
Overall Average Score
Updated 24d ago
Evaluation Results
Method
Method
Links
GSM8K Score
AvgMath Score
Overall Average Score
Equal
Backbone=Qwen3-4B, Dat...
2026.07
90.45
73.62
63.8
RegMix
Backbone=Qwen3-4B, Dat...
2026.07
89.61
65.21
61.4
DMO
Backbone=Qwen3-4B, Dat...
2026.07
89.61
72
63.47
CAUSALMIX
Backbone=Qwen3-4B, Dat...
2026.07
88.86
74.72
66.66
DoReMi
Backbone=Qwen3-4B, Dat...
2026.07
88.55
65.39
62
ODM
Backbone=Qwen3-4B, Dat...
2026.07
88.32
64.74
58.77
Grid
Backbone=Qwen3-4B, Dat...
2026.07
87.34
74.27
64.74
Feedback
Search any
task
Search any
task