Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Accuracy, Recall)
Loading...
81
Accuracy
Full
26.504
40.652
54.8
68.948
Nov 6, 2025
Dec 15, 2025
Jan 23, 2026
Mar 4, 2026
Apr 12, 2026
May 21, 2026
Jun 30, 2026
Accuracy
Recall
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
Recall
Full
Backbone=LLaMA-3.1-8B-...
2026.06
81
100
RaBitQCache
Backbone=LLaMA-3.1-8B-...
2026.06
77
88.8
DS
Backbone=LLaMA-3.1-8B-...
2026.06
77
72.7
SparQ
Backbone=LLaMA-3.1-8B-...
2026.06
77
60.5
Quest
Backbone=LLaMA-3.1-8B-...
2026.06
70
81.3
Baseline
Sparsity=0%, Calib. da...
2025.11
57.6
-
PuzzleMoE
Sparsity=25%, Calib. d...
2025.11
55.4
-
PuzzleMoE
Sparsity=50%, Calib. d...
2025.11
51.7
-
NAEE
Sparsity=25%, Calib. d...
2025.11
48.7
-
NAEE
Sparsity=25%, Calib. d...
2025.11
41.5
-
NAEE
Sparsity=50%, Calib. d...
2025.11
38.8
-
Wanda
Sparsity=50%, Calib. d...
2025.11
32.2
-
NAEE
Sparsity=50%, Calib. d...
2025.11
28.6
-
Feedback
Search any
task
Search any
task