Kimi VL A3B Thinking is the stronger all-rounder.
Scores updated · 13 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 Kimi VL A3B Thinking pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.4points ahead
- Harder college exam questions with imagesMMMU-Pro+5.7points ahead
- College exam questions with charts, maps and diagramsMMMU+2.1points ahead
Where Gemma 3 12B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningKimi VL A3B Thinking
- GPQA DiamondKimi VL A3B Thinking by 7.434.942.3+7.4
Images and chartsKimi VL A3B Thinking
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.
- OCRBench (Acc)Kimi VL A3B Thinking by 162 rating points702864+162 rating
- MMLongBench-DOC (Acc)Kimi VL A3B Thinking by 11.221.332.5+11.2
- MMStar (Acc)Kimi VL A3B Thinking by 8.156.164.2+8.1
- MMLU-ProKimi VL A3B Thinking by 7.960.668.5+7.9
- RealWorldQA (Acc)Kimi VL A3B Thinking by 4.959.164+4.9
- MATH-VisionKimi VL A3B Thinking by 4.732.136.8+4.7
- MathVision (full) (Pass@1)Kimi VL A3B Thinking by 4.732.136.8+4.7
- MMVet (Acc)Kimi VL A3B Thinking by 4.664.969.5+4.6
- VideoMME (w sub.)Kimi VL A3B Thinking by 3.962.166+3.9
- MMBench-EN-v1.1 (Acc)Kimi VL A3B Thinking by 1.474.676+1.4
Questions people ask
Which is better, Gemma 3 12B or Kimi VL A3B Thinking?
Kimi VL A3B Thinking wins all two areas where both have results: reasoning and images and charts. Gemma 3 12B wins none.
How do you compare the two?
We use the 13 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 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.