GPT-4.5 Preview vs o3
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Reasoning · Images and charts · Following instructions
o3 is the stronger all-rounder.
Scores updated · 20 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Coding 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 o3 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+31.1points ahead
- Reasoning about charts from research papersCharXiv (RQ)+23.2points ahead
- Common-sense trick questionsSimpleBench+18.6points ahead
Where GPT-4.5 Preview pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Reasoningo3
- SimpleBencho3 by 18.634.553.1+18.6
- GPQA Diamondo3 by 13.269.582.7+13.2
Images and chartso3
- CharXiv (RQ)o3 by 23.255.478.6+23.2
- MathVistao3 by 14.572.386.8+14.5
- MMMUo3 by 7.775.282.9+7.7
- LMArena · Visiono3 by 19 rating points11951214+19 rating
Other results12 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-1o3 by 50.510.360.8+50.5
- Aider-Polygloto3 by 36.444.981.3+36.4
- SimpleQAGPT-4.5 Preview by 13.162.549.4+13.1
- AA Intelligenceo3 by 10.69.620.2+10.6
- AIR-Bench 2024o3 by 10.374.284.5+10.3
- bbqo3 by 5.99297.9+5.9
- TAU-bench (retail)o3 by 5.568.473.9+5.5
- HarmBencho3 by 2.695.898.4+2.6
- XSTesto3 by 2.295.197.3+2.2
- TAU-bench (airline)o3 by 25052+2
- anthropic_red_teamGPT-4.5 Preview by 1.199.498.3+1.1
- simple_safety_testsGPT-4.5 Preview by 110099+1
Questions people ask
Which is better, GPT-4.5 Preview or o3?
o3 wins all four areas where both have results: coding, reasoning, images and charts and following instructions. GPT-4.5 Preview wins none.
Which is better for coding?
o3. It wins the one coding test both models report.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.