Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Language Understanding on Winogrande, HellaSwag, ARC, MMLU Consolidated
Loading...
71.09
Average Accuracy
Teacher (DeepSeek-V2-Lite)
28.6164
39.6432
50.67
61.6968
May 27, 2026
Average Accuracy
Updated 6d ago
Evaluation Results
Method
Method
Links
Average Accuracy
Teacher (DeepSeek-V2-Lite)
2026.05
71.09
DO-ACP
Scoring=DO-ACP, K=6
2026.05
42.39
SF
Scoring=SF, K=12
2026.05
41.16
DO-ACP
Scoring=DO-ACP, K=12
2026.05
41.07
ACP
Scoring=ACP, K=12
2026.05
40.93
CP
Scoring=CP, K=12
2026.05
40.53
ACP
Scoring=ACP, K=6
2026.05
40.37
SF
Scoring=SF, K=6
2026.05
40.04
CP
Scoring=CP, K=6
2026.05
38.07
Random initialization
2026.05
30.27
Random FFN + teacher attn
2026.05
30.25
Feedback
Search any
task
Search any
task