Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Task Reasoning on MMLU
Loading...
56.7
Pass@1
DCRL
32.988
39.144
45.3
51.456
Mar 17, 2026
Pass@1
Updated 2mo ago
Evaluation Results
Method
Method
Links
Pass@1
DCRL
Backbone=Qwen3-8B-Base
2026.03
56.7
DCRL
Backbone=Qwen3-4B-Base
2026.03
52.6
DCRL
Backbone=Llama3.2-3B-I...
2026.03
33.9
Feedback
Search any
task
Search any
task