GPT-5.3 Codex wins more areas, narrowly.
Scores updated · 23 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software03GPT-5.3 Codex3 of 4 tests · 1 tie
- ReasoningHard problems that need careful thinking03GPT-5.3 Codex3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video01GPT-5.3 Codex1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Agents, images and charts, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.3 Codex pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+26.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.6points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+6points ahead
Where GPT-5.2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.3 Codex
- SWE-bench ProGPT-5.3 Codex by 26.929.956.8+26.9
- Terminal-Bench HardGPT-5.3 Codex by 64753+6
- SciCodeGPT-5.3 Codex by 1.152.153.2+1.1
- LMArena · WebDevtie14151408tie
ReasoningGPT-5.3 Codex
- CritPtGPT-5.3 Codex by 5.311.616.9+5.3
- Humanity's Last ExamGPT-5.3 Codex by 4.837.742.5+4.8
- GPQA DiamondGPT-5.3 Codex by 1.290.391.5+1.2
FactsEven
- AA-Omniscience · AccuracyGPT-5.3 Codex by 8.644.352.9+8.6
- AA-Omniscience · Non-hallucinationGPT-5.2 by 818.810.8+8
Images and chartsGPT-5.3 Codex
- MMMU-ProGPT-5.3 Codex by 3.974.678.5+3.9
Other results10 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- Terminal-Bench 2.0GPT-5.3 Codex by 23.35477.3+23.3
- AA-OmniscienceGPT-5.3 Codex by 11.8-0.910.9+11.8
- metr_re_benchGPT-5.2 by 103525+10
- Artificial Analysis Coding IndexGPT-5.3 Codex by 4.448.753.1+4.4
- AA IntelligenceGPT-5.3 Codex by 2.130.432.5+2.1
- LiveBenchGPT-5.2 by 274.872.8+2
- metr_hcastGPT-5.2 by 1.47775.6+1.4
- τ²-Bench Telecom (AA run)GPT-5.3 Codex by 1.284.886+1.2
- AA Agentic Indextie60.260.5tie
- metr_swaatie99.699.5tie
Questions people ask
Which is better, GPT-5.2 or GPT-5.3 Codex?
GPT-5.3 Codex wins three of the seven areas where both have results: coding, reasoning and images and charts. GPT-5.2 wins none. They are level on agents, facts, long documents and following instructions.
Which is better for coding?
GPT-5.3 Codex. It wins 3 of the 4 coding tests both models report; GPT-5.2 wins none, and 1 is a tie.
Which is cheaper?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; GPT-5.3 Codex costs $1.75 and $14.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.