Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Domain Reasoning on MMLU-Pro Chemistry
Loading...
19.5
Accuracy
KARMA
12.324
14.187
16.05
17.913
Jul 3, 2026
Accuracy
Updated 18d ago
Evaluation Results
Method
Method
Links
Accuracy
KARMA
Backbone=Qwen2.5-7B-In...
2026.07
19.5
Simple SFT (Open-Data)
Backbone=Qwen2.5-7B-In...
2026.07
17.8
Qwen2.5-7B-Instruct
Backbone=Qwen2.5-7B-In...
2026.07
14.8
Simple SFT (KARMA-Data)
Backbone=Qwen2.5-7B-In...
2026.07
12.6
Feedback
Search any
task
Search any
task