Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Fact Verification on FEVER (Accuracy and Tokens)
Loading...
78
Accuracy
Clean Baseline
54.08
60.29
66.5
72.71
Dec 16, 2025
Accuracy
Tokens
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Tokens
Clean Baseline
Backbone=Qwen3-32B, Co...
2025.12
78
11,500
Clean Baseline
Backbone=Qwen3-32B, Co...
2025.12
75
3,200
Clean Baseline
Backbone=Qwen3-32B, Co...
2025.12
72
1,800
Meta-Haste
Backbone=Qwen3-32B, Co...
2025.12
65
11,200
Meta-Haste
Backbone=Qwen3-32B, Co...
2025.12
63
3,000
GSI-Haste
Backbone=Qwen3-32B, Co...
2025.12
62
10,800
Meta-Haste
Backbone=Qwen3-32B, Co...
2025.12
61
1,700
GSI-Haste
Backbone=Qwen3-32B, Co...
2025.12
58
2,900
GSI-Haste
Backbone=Qwen3-32B, Co...
2025.12
55
1,600
Feedback
Search any
task
Search any
task