GPT-5 vs o3
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
GPT-5 is the stronger all-rounder.o3 is cheaper.
Scores updated · 47 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 thinking50GPT-55 of 5 tests
- Images and chartsUnderstanding pictures, charts and video30GPT-53 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up20GPT-52 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own20GPT-52 of 2 tests
- Following instructionsDoing exactly what it is asked20GPT-52 of 2 tests
- CodingWriting and fixing software21GPT-52 of 3 tests
- MathCompetition and research-level math10GPT-51 of 1 test
- Long documentsFinding answers in very long texts10GPT-51 of 1 test
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.
o3 costs 11% 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 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+22.1points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+9.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+8.4points ahead
Where o3 pulls ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+4.5points ahead
Every test, side by side
All 47 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5
- SWE-bench VerifiedGPT-5 by 5.874.969.1+5.8
- Terminal-Bench Hardo3 by 4.532.637.1+4.5
- SciCodeGPT-5 by 1.942.941+1.9
ReasoningGPT-5
- Humanity's Last ExamGPT-5 by 8.428.520.1+8.4
- CritPtGPT-5 by 4.65.71.1+4.6
- SimpleBenchGPT-5 by 3.656.753.1+3.6
- ARC-AGI-2GPT-5 by 3.49.96.5+3.4
- GPQA DiamondGPT-5 by 2.785.482.7+2.7
FactsGPT-5
- AA-Omniscience · Non-hallucinationGPT-5 by 5.917.811.9+5.9
- AA-Omniscience · AccuracyGPT-5 by 1.740.338.6+1.7
- SimpleQA Verifiedtie50.149.4tie
Images and chartsGPT-5
- MMMU-ProGPT-5 by 4.174.270.1+4.1
- CharXiv (RQ)GPT-5 by 2.581.178.6+2.5
- MMMUGPT-5 by 1.384.282.9+1.3
- LMArena · Visiontie12081214tie
Following instructionsGPT-5
- Multi-ChallengeGPT-5 by 9.269.660.4+9.2
- IFBenchGPT-5 by 1.773.171.4+1.7
Other results26 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.
- metr_re_benchGPT-5 by 254015+25
- imo_2025GPT-5 by 21.438.116.7+21.4
- HMMT Feb. 2025GPT-5 by 10.888.377.5+10.8
- FrontierMath (overall)GPT-5 by 10.526.315.8+10.5
- frontiermath_tier_4_v1GPT-5 by 10.412.52.1+10.4
- AA Agentic Indexo3 by 9.626.536.1+9.6
- AIME 2025GPT-5 by 8.294.686.4+8.2
- AA-OmniscienceGPT-5 by 6.8-8.7-15.6+6.8
- Aider-PolyglotGPT-5 by 6.78881.3+6.7
- ARC-AGI-1GPT-5 by 4.965.760.8+4.9
- τ²-Bench Telecom (AA run)GPT-5 by 4.184.880.7+4.1
- metr_hcastGPT-5 by 3.768.464.7+3.7
- AIR-Bench 2024GPT-5 by 3.287.784.5+3.2
- AA IntelligenceGPT-5 by 2.82320.2+2.8
- Tau2 airlineo3 by 2.262.664.8+2.2
- MMLU-ProGPT-5 by 2.187.185+2.1
- ERQAGPT-5 by 1.765.764+1.7
- VideoMMMUGPT-5 by 1.384.683.3+1.3
- LiveCodeBencho3 by 1.283.584.7+1.2
- bbqo3 by 1.196.897.9+1.1
- τ²-Bench (Retail)tie81.180.2tie
- anthropic_red_teamtie99.198.3tie
- HarmBenchtie97.698.4tie
- simple_safety_teststie99.899tie
- Artificial Analysis Coding Indextie37.838.4tie
- XSTesttie97.197.3tie
Questions people ask
Which is better, GPT-5 or o3?
GPT-5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. o3 wins none, but costs 11% less.
Which is better for coding?
GPT-5. It wins 2 of the 3 coding tests both models report; o3 wins 1.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; o3 costs $2.00 and $8.00. That makes o3 about 11% cheaper for the same work.
How do you compare the two?
We use the 47 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 26 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.