Claude Opus 4.8 vs GPT-5.2 Codex
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Math
Wins 1 of 7 areas
Long documents
Claude Opus 4.8 is the stronger all-rounder.GPT-5.2 Codex is cheaper and better at long documents.
Scores updated · 27 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 software51Claude Opus 4.85 of 7 tests · 1 tie
- ReasoningHard problems that need careful thinking40Claude Opus 4.84 of 4 tests
- FactsGetting facts right instead of making them up20Claude Opus 4.82 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude Opus 4.81 of 1 test
- MathCompetition and research-level math10Claude Opus 4.81 of 1 test
- Long documentsFinding answers in very long texts01GPT-5.2 Codex1 of 1 test
- Following instructionsDoing exactly what it is asked11Even1 each
Agents, math and long documents 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-5.2 Codex costs 48% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.8 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+21.2points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+15.8points ahead
Where GPT-5.2 Codex pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.4points ahead
- Reasons across sets of long documentsAA-LCR+4.6points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+1.8points ahead
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- LMArena · WebDevClaude Opus 4.8 by 217 rating points15561339+217 rating
- Terminal-Bench HardClaude Opus 4.8 by 21.258.337.1+21.2
- SWE-bench VerifiedClaude Opus 4.8 by 15.888.672.8+15.8
- SWE-bench ProClaude Opus 4.8 by 12.869.256.4+12.8
- LiveBench · CodingGPT-5.2 Codex by 1.881.883.6+1.8
- LiveBench · Agentic CodingClaude Opus 4.8 by 1.150.549.4+1.1
- SciCodetie54.454.6tie
ReasoningClaude Opus 4.8
- Humanity's Last ExamClaude Opus 4.8 by 1348.735.7+13
- CritPtClaude Opus 4.8 by 12.220.98.7+12.2
- LiveBench · ReasoningClaude Opus 4.8 by 11.589.277.7+11.5
- GPQA DiamondClaude Opus 4.8 by 2.19289.9+2.1
FactsClaude Opus 4.8
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 34.160.726.6+34.1
- AA-Omniscience · AccuracyClaude Opus 4.8 by 7.748.841.1+7.7
Following instructionsEven
- IFBenchGPT-5.2 Codex by 15.462.277.6+15.4
- LiveBench · Instruction FollowingClaude Opus 4.8 by 5.57266.5+5.5
Other results9 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.
- Artificial Analysis Coding IndexClaude Opus 4.8 by 31.374.343+31.3
- AA-OmniscienceClaude Opus 4.8 by 3128.8-2.2+31
- AA Agentic IndexGPT-5.2 Codex by 13.942.656.5+13.9
- AA IntelligenceClaude Opus 4.8 by 13.341.828.5+13.3
- livebench_data_analysisGPT-5.2 Codex by 12.26678.2+12.2
- Terminal-Bench 2.0Claude Opus 4.8 by 10.674.664+10.6
- livebench_languageClaude Opus 4.8 by 679.773.7+6
- LiveBenchClaude Opus 4.8 by 2.977.274.3+2.9
- τ²-Bench Telecom (AA run)Claude Opus 4.8 by 2.394.492.1+2.3
Questions people ask
Which is better, Claude Opus 4.8 or GPT-5.2 Codex?
Claude Opus 4.8 wins five of the seven areas where both have results: coding, agents, reasoning, facts and math. GPT-5.2 Codex wins long documents, and costs 48% less. They are level on following instructions.
Which is better for coding?
Claude Opus 4.8. It wins 5 of the 7 coding tests both models report; GPT-5.2 Codex wins 1, and 1 is a tie.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.2 Codex costs $1.75 and $14.00. That makes GPT-5.2 Codex about 48% cheaper for the same work.
How do you compare the two?
We use the 27 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.