Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on MMLU-CK (test)
Loading...
60.95
Accuracy
PubMed Reasoner
51.0388
53.6119
56.185
58.7581
Mar 28, 2026
Accuracy
Updated 2mo ago
Evaluation Results
Method
Method
Links
Accuracy
PubMed Reasoner
Backbone=Qwen2.5-72B
2026.03
60.95
Self-reflection agent
Backbone=Qwen2.5-72B
2026.03
59.67
Without retrieval
Backbone=Qwen2.5-72B
2026.03
58.36
Without retrieval
Backbone=Qwen2.5-7B
2026.03
56.64
Self-reflection agent
Backbone=Qwen2.5-7B
2026.03
56.11
PubMed Reasoner
Backbone=Qwen2.5-7B
2026.03
56.09
Without retrieval
Backbone=Qwen2.5-1.5B
2026.03
55.67
Self-reflection agent
Backbone=Qwen2.5-1.5B
2026.03
51.44
PubMed Reasoner
Backbone=Qwen2.5-1.5B
2026.03
51.42
Feedback
Search any
task
Search any
task