Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on OpenBookQA (OpQA)
Loading...
47
OpQA Score
STL
37.64
40.07
42.5
44.93
Feb 10, 2026
OpQA Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
OpQA Score
STL
Base Model=Qwen2.5-7B
2026.02
47
STL-aug
Base Model=Qwen2.5-7B
2026.02
47
Surgical
Base Model=Qwen2.5-7B
2026.02
47
STL
Base Model=LLaMA-3-8B
2026.02
45
STL-aug
Base Model=LLaMA-3-8B
2026.02
45
Surgical
Base Model=LLaMA-3-8B
2026.02
45
SCANS
Base Model=Qwen2.5-7B
2026.02
44
DCR
Base Model=Qwen2.5-7B
2026.02
44
SCANS
Base Model=LLaMA-3-8B
2026.02
44
STL
Base Model=Qwen2.5-1.5B
2026.02
41
STL-aug
Base Model=Qwen2.5-1.5B
2026.02
41
Surgical
Base Model=Qwen2.5-1.5B
2026.02
40
SCANS
Base Model=Qwen2.5-1.5B
2026.02
39
DCR
Base Model=LLaMA-3-8B
2026.02
39
DCR
Base Model=Qwen2.5-1.5B
2026.02
38
Feedback
Search any
task
Search any
task