GPT-4o is the stronger all-rounder.
Scores updated · 16 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 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
- Harder college exam questions with imagesMMMU-Pro+13.1points ahead
- College exam questions with charts, maps and diagramsMMMU+10.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+10.3points ahead
Where Kimi VL A3B Thinking pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsGPT-4o
Other results13 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.
- ScreenSpot-V2Kimi VL A3B Thinking by 73.318.191.4+73.3
- RealWorldQA (Acc)GPT-4o by 11.475.464+11.4
- VideoMME (w sub.)GPT-4o by 11.277.266+11.2
- MMLongBench-DOC (Acc)GPT-4o by 10.342.832.5+10.3
- MMLUKimi VL A3B Thinking by 8.273.882+8.2
- MMBench-EN-v1.1 (Acc)GPT-4o by 7.183.176+7.1
- MATHKimi VL A3B Thinking by 6.585.391.8+6.5
- MATH-VisionKimi VL A3B Thinking by 6.430.436.8+6.4
- MathVision (full) (Pass@1)Kimi VL A3B Thinking by 6.430.436.8+6.4
- MMLU-ProGPT-4o by 6.274.768.5+6.2
- OCRBench (Acc)Kimi VL A3B Thinking by 49 rating points815864+49 rating
- MMStar (Acc)tie64.764.2tie
- MMVet (Acc)tie69.169.5tie
Questions people ask
Which is better, GPT-4o or Kimi VL A3B Thinking?
GPT-4o wins all two areas where both have results: reasoning and images and charts. Kimi VL A3B Thinking wins none.
How do you compare the two?
We use the 16 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 13 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.