Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Localization on MuLocBench
Loading...
6.4
Mean Latency (s)
BM25
-18.772
151.139
321.05
490.961
May 8, 2026
Mean Latency (s)
Median Latency (s)
Updated 15d ago
Evaluation Results
Method
Method
Links
Mean Latency (s)
Median Latency (s)
BM25
2026.05
6.4
1.6
mini-swe-agent
Model=GPT-5.2
2026.05
32.3
23.6
Agentless
Model=GPT-5.2
2026.05
39.3
15.8
SWE-agent
Model=GPT-5.2
2026.05
72.3
58.8
Claude Code
Interface=Native
2026.05
98.3
81.7
LARGER
Model=GPT-5.2
2026.05
99.9
71.6
CoSIL
Model=GPT-5.2
2026.05
109.7
58.1
Codex
Interface=Native
2026.05
139.9
132.8
LocAgent
Model=GPT-5.2
2026.05
263.4
65.7
OpenHands
Interface=Native
2026.05
635.7
474.6
Feedback
Search any
task
Search any
task