Final specialized Codex release before coding was folded into mainline GPT-5.4. Peak on LiveCodeBench and Terminal-Bench.
| Benchmark | Score | Rank |
|---|---|---|
MMLU Tests knowledge across 57 subjects from STEM to humanities | 93% | #4 / 54 |
OSWorld Computer use in real desktop environments | 74% | #4 / 13 |
SWE-bench Real-world GitHub issue resolution | 80% | #6 / 39 |
Terminal Agentic terminal coding tasks requiring multi-step execution | 77.3% | #8 / 56 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 87.3% | #8 / 48 |
GPQA PhD-level science questions even experts struggle with | 92.6% | #9 / 73 |
hleArtificial Analysis | 39.9% | #11 / 61 |
ARC-AGI Novel reasoning tasks requiring fluid intelligence | 54% | #13 / 26 |
MATH Competition-level mathematics problems | 96% | #15 / 50 |
HumanEval Coding ability - generating correct Python functions | 93% | #24 / 50 |
MMMUArtificial Analysis College-level multimodal reasoning across 30+ disciplines | 78.5% | #27 / 46 |