Codex Mini — Retired model
codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.
Technical specifications
Independent benchmarks
Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.
Intelligence 31
Coding
Math 92
MMLU 82
GPQA 81
This modelCategory leader
Overall intelligence
#133out of 573 models
Aggregated across academic benchmarks
Math reasoning
#18out of 269 models
AIME / MATH-500 / SciCode
Time to first token
🥇
#1out of 586 models
AA 全球 p50：0.00 秒
Intelligence
31
Top 23%This model31
Category leader61
Median15
Math
92
Top 7%This model92
Category leader99
Median53
MMLU Pro
82%
—This model82%
Category leader90%
Median75%
GPQA
81%
—This model81%
Category leader94%
Median69%
LiveCodeBench
84%
—This model84%
Category leader42%
Median42%
HLE
17%
—This model17%
Category leader53%
Median7%
SciCode
43%
—This model43%
Category leader60%
Median33%
IFBench
68%
—This model68%
Category leader83%
Median44%
τ²-Bench Telecom
63%
—This model63%
Category leader99%
Median46%
AA-LCR
63%
—This model63%
Category leader76%
Median40%
Terminal-Bench Hard
33%
—This model33%
Category leader66%
Median14%
Top 5 — CodingCoding Index leaderboard
1GPT-5.6 Sol (xhigh)
openai/gpt-5-6-sol-xhigh78$5 / $304GPT-5.6 Sol (high)
openai/gpt-5-6-sol-high77$5 / $305Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
anthropic/claude-opus-5-xhigh77$5 / $25AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →
Frequently Asked Questions
Can I still use the retired Codex Mini model?
No. Codex Mini has been retired and is retained here only as a historical reference. See the active alternatives linked on this page.
Relay integrity checks
No integrity-check data is available for this model yet.
BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.
View the full integrity report →Related models and links
More from this provider: OpenAI