Grok 3 Beta is the stronger all-rounder.GPT-4o mini is cheaper.
Scores updated · 11 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.
Reasoning and images and charts 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 96% 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 Grok 3 Beta pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+32.8points ahead
- College exam questions with charts, maps and diagramsMMMU+13.8points ahead
Where GPT-4o mini pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results9 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-PolyglotGrok 3 Beta by 49.73.653.3+49.7
- HarmBenchGPT-4o mini by 39.684.945.3+39.6
- SimpleQAGrok 3 Beta by 33.79.943.6+33.7
- LiveCodeBenchGrok 3 Beta by 21.535.557+21.5
- MMLU-ProGrok 3 Beta by 18.261.779.9+18.2
- AIR-Bench 2024GPT-4o mini by 556.351.3+5
- anthropic_red_teamGPT-4o mini by 2.898.395.5+2.8
- simple_safety_testsGPT-4o mini by 197.896.8+1
- XSTesttie9696.4tie
Questions people ask
Which is better, GPT-4o mini or Grok 3 Beta?
Grok 3 Beta wins all two areas where both have results: reasoning and images and charts. GPT-4o mini wins none, but costs 96% less.
Which is cheaper?
GPT-4o mini costs $0.15 per million input tokens and $0.60 per million output tokens; Grok 3 Beta costs $3.00 and $15.00. That makes GPT-4o mini about 96% cheaper for the same work.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.