Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Truncated CoT Answering on FOLIO
Loading...
0.35
AOC
Faithfulness Only
0.24288
0.27069
0.2985
0.32631
Feb 18, 2026
AOC
Updated 4d ago
Evaluation Results
Method
Method
Links
AOC
Faithfulness Only
Backbone=Qwen3-14B
2026.02
0.35
REMUL
Backbone=Qwen3-14B
2026.02
0.332
MAT-Steer
Backbone=Qwen3-14B
2026.02
0.32
Balanced Rewards
Backbone=Qwen3-14B
2026.02
0.299
Original
Backbone=Qwen3-14B
2026.02
0.284
Hint Optimized
Backbone=Qwen3-14B
2026.02
0.268
Correctness Only
Backbone=Qwen3-14B
2026.02
0.247
Feedback
Search any
task
Search any
task