Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Issue Resolution on SWE-bench Lite (test)
Loading...
185
Resolved Issues Count
Codex CLI GPT-5.4
151.72
160.36
169
177.64
May 7, 2026
Resolved Issues Count
Total Cost ($)
Total Tokens (M)
Updated 23d ago
Evaluation Results
Method
Method
Links
Resolved Issues Count
Total Cost ($)
Total Tokens (M)
Codex CLI GPT-5.4
Config=default, Effort...
2026.05
185
236.73
220.67
Codex CLI GPT-5.4
Config=default, Effort...
2026.05
172
161.82
155.96
Spell GPT-5.4
Config=default, Effort...
2026.05
171
102.12
51.37
Spell GPT-5.4
Config=default, Effort...
2026.05
171
177.38
49.26
Codex CLI GPT-5.4
Config=default, Effort...
2026.05
170
136.79
134.09
Spell GPT-5.4
Config=default, Effort...
2026.05
153
68.94
74.3
Feedback
Search any
task
Search any
task