Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Resolution on Software Repository
Loading...
24.32
Coverage
TIDE
4.0608
9.3204
14.58
19.8396
Jun 3, 2026
Coverage
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Coverage
F1 Score
TIDE
Backbone=Gemini 3.5 Flash
2026.06
24.32
26.98
TIDE
Backbone=Claude Sonnet...
2026.06
15.79
17.76
TIDE
Backbone=GPT-5 mini
2026.06
15.52
17.39
MULTI-AGENT
Backbone=Gemini 3.5 Flash
2026.06
15.32
18.89
SINGLE-AGENT
Backbone=Gemini 3.5 Flash
2026.06
15.08
18.71
SINGLE-AGENT
Backbone=GPT-5 mini
2026.06
12.19
13.27
MULTI-AGENT
Backbone=GPT-5 mini
2026.06
9.89
12.39
SINGLE-AGENT
Backbone=Claude Sonnet...
2026.06
9.84
12.34
MULTI-AGENT
Backbone=Claude Sonnet...
2026.06
8.88
11.01
TIDE
Backbone=Qwen 3.6 Flash
2026.06
8.47
9.7
MULTI-AGENT
Backbone=Qwen 3.6 Flash
2026.06
5.83
6.5
SINGLE-AGENT
Backbone=Qwen 3.6 Flash
2026.06
4.84
5.76
Feedback
Search any
task
Search any
task