GPT-4o wins more areas, narrowly.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the two 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 rests on a single test.
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 GPT-4o pulls ahead
- Code for real scientific research problemsSciCode+21.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+17.7points ahead
Where Mistral Medium (Non-Reasoning) pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.7points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA DiamondGPT-4o by 17.752.634.9+17.7
- Humanity's Last ExamMistral Medium (Non-Reasoning) by 1.71.83.5+1.7
Other results7 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.
- NarrativeQAGPT-4o by 34.679.544.9+34.6
- MATHGPT-4o by 28.785.356.5+28.7
- naturalquestions_closedbookGPT-4o by 20.649.629+20.6
- GSM8KGPT-4o by 20.390.970.6+20.3
- OpenBookQAGPT-4o by 13.896.883+13.8
- MMLUGPT-4o by 1273.861.8+12
- AA IntelligenceGPT-4o by 1.87.35.5+1.8
Questions people ask
Which is better, GPT-4o or Mistral Medium (Non-Reasoning)?
GPT-4o wins one of the two areas where both have results: coding. Mistral Medium (Non-Reasoning) wins none. They are level on reasoning.
Which is better for coding?
GPT-4o. It wins the one coding test both models report.
How do you compare the two?
We use the 10 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 7 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.