Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Score & Speedup)
Loading...
77.6
Accuracy
LSP
-1.8872
18.7489
39.385
60.0211
May 26, 2025
Jul 12, 2025
Aug 28, 2025
Oct 14, 2025
Nov 30, 2025
Jan 16, 2026
Mar 5, 2026
Accuracy
Inference Speedup
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Inference Speedup
LSP
Model=LLaDA-8B, Infere...
2026.03
77.6
1.51
Full
Model=LLaDA-8B, Infere...
2026.03
77.1
-
LSP
Model=Dream-7B, Infere...
2026.03
75.4
1.69
Full
Model=Dream-7B, Infere...
2026.03
75.3
-
Llama3.2-1B
Forgetting Task=none
2025.05
19.71
-
LWF
Forgetting Task=dental
2025.05
10.4
-
LWF
Forgetting Task=mixed
2025.05
6.95
-
LWF
Forgetting Task=qasc
2025.05
5.38
-
LWF
Forgetting Task=sst5
2025.05
2.67
-
LWF
Forgetting Task=psychol
2025.05
1.17
-
Feedback
Search any
task
Search any
task