GPT-5.2 vs o3
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 0 of 8 areas
—
GPT-5.2 is the stronger all-rounder.o3 is cheaper.
Scores updated · 37 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 thinking41GPT-5.24 of 5 tests
- CodingWriting and fixing software30GPT-5.23 of 3 tests
- Images and chartsUnderstanding pictures, charts and video31GPT-5.23 of 4 tests
- AgentsCarrying out multi-step tasks on its own20GPT-5.22 of 2 tests
- FactsGetting facts right instead of making them up21GPT-5.22 of 3 tests
- MathCompetition and research-level math10GPT-5.21 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.21 of 1 test
- Long documentsFinding answers in very long texts11Even1 each
Math 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.
o3 costs 37% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5.2 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+46.4points ahead
- Real work tasks from 44 professionsGDPVal+35.5points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+34.1points ahead
Where o3 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+12.3points ahead
- Common-sense trick questionsSimpleBench+7.3points ahead
- Questions about very long textsLongBench v2+4.3points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.2
- SciCodeGPT-5.2 by 11.152.141+11.1
- SWE-bench VerifiedGPT-5.2 by 10.98069.1+10.9
- Terminal-Bench HardGPT-5.2 by 9.94737.1+9.9
AgentsGPT-5.2
- GDPValGPT-5.2 by 35.548.312.8+35.5
- BrowseCompGPT-5.2 by 16.165.849.7+16.1
ReasoningGPT-5.2
- ARC-AGI-2GPT-5.2 by 46.452.96.5+46.4
- Humanity's Last ExamGPT-5.2 by 17.637.720.1+17.6
- CritPtGPT-5.2 by 10.511.61.1+10.5
- GPQA DiamondGPT-5.2 by 7.690.382.7+7.6
- SimpleBencho3 by 7.345.853.1+7.3
FactsGPT-5.2
- SimpleQA Verifiedo3 by 12.337.149.4+12.3
- AA-Omniscience · Non-hallucinationGPT-5.2 by 6.918.811.9+6.9
- AA-Omniscience · AccuracyGPT-5.2 by 5.744.338.6+5.7
Images and chartsGPT-5.2
- MMMU-ProGPT-5.2 by 4.574.670.1+4.5
- MathVistao3 by 482.886.8+4
- CharXiv (RQ)GPT-5.2 by 3.582.178.6+3.5
- LMArena · VisionGPT-5.2 by 32 rating points12461214+32 rating
Long documentsEven
- AA-LCRGPT-5.2 by 882.774.7+8
- LongBench v2o3 by 4.354.558.8+4.3
Other results16 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.
- ARC-AGI-1GPT-5.2 by 25.486.260.8+25.4
- FrontierMath (overall)GPT-5.2 by 24.540.315.8+24.5
- AA Agentic IndexGPT-5.2 by 24.160.236.1+24.1
- HMMT Feb. 2025GPT-5.2 by 22.510077.5+22.5
- metr_re_benchGPT-5.2 by 203515+20
- frontiermath_tier_4_v1GPT-5.2 by 16.718.82.1+16.7
- AA-OmniscienceGPT-5.2 by 14.6-0.9-15.6+14.6
- AIME 2025GPT-5.2 by 13.610086.4+13.6
- metr_hcastGPT-5.2 by 12.37764.7+12.3
- Artificial Analysis Coding IndexGPT-5.2 by 10.348.738.4+10.3
- AA IntelligenceGPT-5.2 by 10.230.420.2+10.2
- LiveCodeBenchGPT-5.2 by 4.38984.7+4.3
- τ²-Bench Telecom (AA run)GPT-5.2 by 4.184.880.7+4.1
- VideoMMMUGPT-5.2 by 2.685.983.3+2.6
- τ²-Bench (Retail)GPT-5.2 by 1.88280.2+1.8
- MMLU-ProGPT-5.2 by 1.786.785+1.7
Questions people ask
Which is better, GPT-5.2 or o3?
GPT-5.2 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. o3 wins none, but costs 37% less. They are level on long documents.
Which is better for coding?
GPT-5.2. It wins 3 of the 3 coding tests both models report; o3 wins none.
Which is cheaper?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; o3 costs $2.00 and $8.00. That makes o3 about 37% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.