The two are evenly matched.GPT-4o mini is better at reasoning; GPT-4 at following instructions.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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.
Agents, reasoning 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 99% 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-4o mini pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.7points ahead
Where GPT-4 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.2points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
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.
- MATHGPT-4o mini by 37.780.242.5+37.7
- HumanEvalGPT-4o mini by 20.287.267+20.2
- MGSMGPT-4o mini by 12.58774.5+12.5
- GSM8KGPT-4 by 8.984.393.2+8.9
- AIR-Bench 2024GPT-4 by 7.956.364.2+7.9
- naturalquestions_closedbookGPT-4 by 7.138.545.7+7.1
- MMLUGPT-4 by 6.766.873.5+6.7
- OpenBookQAGPT-4 by 49296+4
- Artificial Analysis Coding IndexGPT-4 by 1.711.413.1+1.7
- DROPGPT-4 by 1.279.780.9+1.2
- AA Intelligencetie6.76.7tie
- NarrativeQAtie76.876.8tie
Questions people ask
Which is better, GPT-4o mini or GPT-4?
GPT-4o mini and GPT-4 each win one of the three areas where both have results. GPT-4o mini wins reasoning; GPT-4 wins following instructions. GPT-4o mini costs 99% less. They are level on agents.
Which is cheaper?
GPT-4o mini costs $0.15 per million input tokens and $0.60 per million output tokens; GPT-4 costs $30.00 and $60.00. That makes GPT-4o mini about 99% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 3 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.