Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Checkpoint Selection on REPO-PROMPTS, MS-COCO, and PartiPrompts
Loading...
4.42
Intent Score
Check-in
2.0488
2.6644
3.28
3.8956
Mar 24, 2026
Intent Score
Human Preference
Updated 25d ago
Evaluation Results
Method
Method
Links
Intent Score
Human Preference
Check-in
2026.03
4.42
100
Stylus
2026.03
3.68
82.1
Reranker
2026.03
3.21
85.7
Random
2026.03
2.14
89.1
Feedback
Search any
task
Search any
task
