Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering Question Answering on SWE-QA Reflex
Loading...
8.15
Overall Score
LaMR
7.734
7.842
7.95
8.058
May 14, 2026
Overall Score
Interaction Rounds
Tokens (K)
Updated 16d ago
Evaluation Results
Method
Method
Links
Overall Score
Interaction Rounds
Tokens (K)
LaMR
Backbone=Claude Opus 4.6
2026.05
8.15
27.4
661.9
SWE-Pruner
Backbone=Claude Opus 4.6
2026.05
8.14
30.7
737
SWE-Pruner
Backbone=Claude Sonnet...
2026.05
8.07
32.4
901.5
Unpruned
Backbone=Claude Opus 4.6
2026.05
8.06
26.9
677
LaMR
Backbone=Claude Sonnet...
2026.05
7.88
29.2
753.2
Unpruned
Backbone=Claude Sonnet...
2026.05
7.75
33.2
1,096.3
Feedback
Search any
task
Search any
task