GPT-4o vs Magistral Medium 1
Wins 4 of 6 areas
Coding · Facts · Long documents · Following instructions
Wins 2 of 6 areas
Agents · Reasoning
GPT-4o is the stronger all-rounder.Magistral Medium 1 is better at reasoning.
Scores updated · 21 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.
- FactsGetting facts right instead of making them up20GPT-4o2 of 2 tests
- CodingWriting and fixing software10GPT-4o1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-4o1 of 1 test
- ReasoningHard problems that need careful thinking02Magistral Medium 12 of 4 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own01Magistral Medium 11 of 1 test
Agents, long documents 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 GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+21.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+10.9points ahead
- Code for real scientific research problemsSciCode+3.6points ahead
Where Magistral Medium 1 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+15.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+8points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningMagistral Medium 1
- GPQA DiamondMagistral Medium 1 by 15.352.667.9+15.3
- Humanity's Last ExamMagistral Medium 1 by 81.89.8+8
- CritPttie00.3tie
- ARC-AGI-2tie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 21.462.140.7+21.4
- AA-Omniscience · AccuracyGPT-4o by 3.423.720.3+3.4
Other results10 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.
- AIME 2024Magistral Medium 1 by 61.49.370.7+61.4
- AIME 2025Magistral Medium 1 by 53.211.764.9+53.2
- AA-OmniscienceGPT-4o by 16.4-10.5-26.9+16.4
- Aider-PolyglotMagistral Medium 1 by 16.430.747.1+16.4
- LiveCodeBenchMagistral Medium 1 by 1238.350.3+12
- Artificial Analysis Coding IndexGPT-4o by 8.224.216+8.2
- AA Agentic IndexMagistral Medium 1 by 7.38.415.7+7.3
- τ²-Bench Telecom (AA run)GPT-4o by 5.828.923.1+5.8
- AA IntelligenceMagistral Medium 1 by 1.87.39.1+1.8
- ARC-AGI-1Magistral Medium 1 by 1.64.56.1+1.6
Questions people ask
Which is better, GPT-4o or Magistral Medium 1?
GPT-4o wins four of the six areas where both have results: coding, facts, long documents and following instructions. Magistral Medium 1 wins agents and reasoning.
Which is better for coding?
GPT-4o. It wins 1 of the 2 coding tests both models report; Magistral Medium 1 wins none, and 1 is a tie.
How do you compare the two?
We use the 21 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 10 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.