Claude Opus 4.5 vs GPT-5.3 Codex
Wins 0 of 7 areas
—
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
GPT-5.3 Codex is the stronger all-rounder.
Scores updated · 24 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.
- ReasoningHard problems that need careful thinking03GPT-5.3 Codex3 of 3 tests
- CodingWriting and fixing software13GPT-5.3 Codex3 of 4 tests
- Images and chartsUnderstanding pictures, charts and video01GPT-5.3 Codex1 of 1 test
- Long documentsFinding answers in very long texts01GPT-5.3 Codex1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5.3 Codex1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
- FactsGetting facts right instead of making them up11Even1 each
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.
GPT-5.3 Codex costs 48% less for the same work.
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
- Follows unfamiliar, precisely checkable instructionsIFBench+17.4points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+12.4points ahead
- Research-level physics problemsCritPt+12.3points ahead
Where Claude Opus 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+28.2points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+1.6points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.3 Codex
- LMArena · WebDevClaude Opus 4.5 by 60 rating points14691409+60 rating
- Terminal-Bench HardGPT-5.3 Codex by 64753+6
- SWE-bench ProGPT-5.3 Codex by 4.85256.8+4.8
- SciCodeGPT-5.3 Codex by 3.749.553.2+3.7
AgentsEven
- GDPValGPT-5.3 Codex by 1.747.349+1.7
- OSWorld-VerifiedClaude Opus 4.5 by 1.666.364.7+1.6
ReasoningGPT-5.3 Codex
- Humanity's Last ExamGPT-5.3 Codex by 12.430.142.5+12.4
- CritPtGPT-5.3 Codex by 12.34.616.9+12.3
- GPQA DiamondGPT-5.3 Codex by 4.986.691.5+4.9
FactsEven
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 28.23910.8+28.2
- AA-Omniscience · AccuracyGPT-5.3 Codex by 6.346.652.9+6.3
Following instructionsGPT-5.3 Codex
- IFBenchGPT-5.3 Codex by 17.45875.4+17.4
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 1859.377.3+18
- metr_re_benchClaude Opus 4.5 by 154025+15
- Artificial Analysis Coding IndexGPT-5.3 Codex by 5.347.853.1+5.3
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 3.589.586+3.5
- AA IntelligenceGPT-5.3 Codex by 3.429.132.5+3.4
- LiveBenchClaude Opus 4.5 by 3.27672.8+3.2
- AA-OmniscienceClaude Opus 4.5 by 3.11410.9+3.1
- metr_hcastGPT-5.3 Codex by 2.273.475.6+2.2
- AA Agentic Indextie59.660.5tie
- metr_swaatie99.599.5tie
Questions people ask
Which is better, Claude Opus 4.5 or GPT-5.3 Codex?
GPT-5.3 Codex wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. Claude Opus 4.5 wins none. They are level on agents and facts.
Which is better for coding?
GPT-5.3 Codex. It wins 3 of the 4 coding tests both models report; Claude Opus 4.5 wins 1.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.3 Codex costs $1.75 and $14.00. That makes GPT-5.3 Codex about 48% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 14 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.