Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conflict Resolution on MCR-BENCH
Loading...
45.9
Accuracy (Neutral)
CAAD
-0.796
11.327
23.45
35.573
Jun 22, 2026
Accuracy (Neutral)
Accuracy (Faithful)
Accuracy (Adversarial)
Accuracy (Irrelevant)
Shift
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Neutral)
Accuracy (Faithful)
Accuracy (Adversarial)
Accuracy (Irrelevant)
Shift
CAAD
Model Size=3B, Decodin...
2026.06
45.9
82.8
11.8
45.5
79.03
Student
Model Size=3B, Decodin...
2026.06
41
96.9
0.5
40.9
100
Teacher
Model Size=8B, Decodin...
2026.06
11.2
51.4
15
41.8
83.96
Teacher
Model Size=8B, Decodin...
2026.06
3.9
98.6
1.1
41.2
97.37
Student
Model Size=3B, Decodin...
2026.06
1.4
97.4
1
34
90.65
Student
Model Size=3B, Decodin...
2026.06
1
56.6
7.4
26.9
87.5
Feedback
Search any
task
Search any
task
