Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Formulation QA on Formulation QA (Standard)
Loading...
58.7
Accuracy
w summary
40.708
45.379
50.05
54.721
Apr 8, 2026
Accuracy
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
w summary
Token=30*5, Backbone=L...
2026.04
58.7
vanilla RAG
Token=512*3, Backbone=...
2026.04
56.7
SciDC
Token=30*5, Backbone=L...
2026.04
56.7
w GPT-5
Token=50*3, Backbone=L...
2026.04
52.7
SciDC
Token=30*5, Backbone=L...
2026.04
47.5
w wiki
Token=800*5, Backbone=...
2026.04
47.3
vanilla RAG
Token=512*3, Backbone=...
2026.04
46.1
w summary
Token=30*5, Backbone=L...
2026.04
46
w GPT-5
Token=50*3, Backbone=L...
2026.04
45.5
Original
Token=0, Backbone=LLaM...
2026.04
43.3
w wiki
Token=800*5, Backbone=...
2026.04
41.7
Original
Token=0, Backbone=LLaM...
2026.04
41.4
Feedback
Search any
task
Search any
task