Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge Combination on KID-Bench Category B v2
Loading...
68
Accuracy
D2L Baseline
63.84
64.92
66
67.08
Apr 26, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
D2L Baseline
Backbone=Gemma-2B, Dec...
2026.04
68
SLB
Backbone=Gemma-2B, Dec...
2026.04
68
Conflict-Aware
Backbone=Gemma-2B, Dec...
2026.04
64
Feedback
Search any
task
Search any
task