Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Logical Reasoning on LogiQA (Pass@1, FLOPS)
Loading...
48.61
Pass@1 Accuracy
MFS (Ours)
32.7188
36.8444
40.97
45.0956
Jan 21, 2026
Pass@1 Accuracy
FLOPS
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
FLOPS
MFS (Ours)
Backbone=LLaMA3.1-8B-I...
2026.01
48.61
-
ϕ-Decoding
Backbone=LLaMA3.1-8B-I...
2026.01
48.39
-
Predictive Decoding
Backbone=LLaMA3.1-8B-I...
2026.01
46.7
-
Tree-of-Thoughts
Backbone=LLaMA3.1-8B-I...
2026.01
45.93
-
Guided Decoding
Backbone=LLaMA3.1-8B-I...
2026.01
43.47
-
MFS (Ours)
Backbone=Mistral-v0.3-...
2026.01
43.16
-
ϕ-Decoding
Backbone=Mistral-v0.3-...
2026.01
43.01
-
MCTS
Backbone=LLaMA3.1-8B-I...
2026.01
42.7
-
Tree-of-Thoughts
Backbone=Mistral-v0.3-...
2026.01
41.63
-
MCTS
Backbone=Mistral-v0.3-...
2026.01
40.71
-
Predictive Decoding
Backbone=Mistral-v0.3-...
2026.01
39.78
-
Auto-Regressive (CoT)
Backbone=Mistral-v0.3-...
2026.01
37.02
-
Guided Decoding
Backbone=Mistral-v0.3-...
2026.01
36.71
-
Auto-Regressive (CoT)
Backbone=LLaMA3.1-8B-I...
2026.01
33.33
-
Feedback
Search any
task
Search any
task