GPT-4o mini vs o3
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Images and charts · Following instructions
o3 is the stronger all-rounder.GPT-4o mini is cheaper.
Scores updated · 25 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 thinking03o33 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03o33 of 3 tests
- CodingWriting and fixing software02o32 of 2 tests
- AgentsCarrying out multi-step tasks on its own01o31 of 1 test
- FactsGetting facts right instead of making them up01o31 of 1 test
- Following instructionsDoing exactly what it is asked01o31 of 1 test
Agents, facts 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-4o mini costs 93% 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 o3 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+60.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+41.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+40.4points ahead
Where GPT-4o mini pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Reasoningo3
- GPQA Diamondo3 by 40.142.682.7+40.1
- Humanity's Last Examo3 by 15.94.220.1+15.9
- ARC-AGI-2o3 by 6.506.5+6.5
Images and chartso3
Other results14 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.
- Aider-Polygloto3 by 77.73.681.3+77.7
- livecodebench_mediumo3 by 64.625.289.8+64.6
- livecodebench_hardo3 by 61.74.366+61.7
- LiveCodeBencho3 by 49.235.584.7+49.2
- SimpleQAo3 by 39.59.949.4+39.5
- AIR-Bench 2024o3 by 28.256.384.5+28.2
- Artificial Analysis Coding Indexo3 by 2711.438.4+27
- MMLU-Proo3 by 23.361.785+23.3
- livecodebench_easyo3 by 17.481.799.1+17.4
- AA Intelligenceo3 by 13.56.720.2+13.5
- HarmBencho3 by 13.584.998.4+13.5
- XSTesto3 by 1.39697.3+1.3
- simple_safety_testso3 by 1.297.899+1.2
- anthropic_red_teamtie98.398.3tie
Questions people ask
Which is better, GPT-4o mini or o3?
o3 wins all six areas where both have results: coding, agents, reasoning, facts, images and charts and following instructions. GPT-4o mini wins none, but costs 93% less.
Which is better for coding?
o3. It wins 2 of the 2 coding tests both models report; GPT-4o mini wins none.
Which is cheaper?
GPT-4o mini costs $0.15 per million input tokens and $0.60 per million output tokens; o3 costs $2.00 and $8.00. That makes GPT-4o mini about 93% cheaper for the same work.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.