Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Gemma 3 12B vs Qwen2.5 VL 72B

Google · released

Wins 0 of 1 area

—

Alibaba · released

Wins 1 of 1 area

Images and charts

Qwen2.5 VL 72B is the stronger all-rounder.

Scores updated · 17 tests both models report · How we compare

Where each one wins

Tests won in each of the one area 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.

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.

Gemma 3 12B$0.05 to read · $0.15 to write$0.20Price from deepinfra
Qwen2.5 VL 72BNo current price is tracked.

The biggest differences

The tests each model wins by the widest margin, up to three each. Scores are out of 100.

Where Qwen2.5 VL 72B pulls ahead

  • Harder college exam questions with imagesMMMU-Pro+13.6points aheadQwen2.5 VL 72B51.1Gemma 3 12B37.5
  • Math problems shown in pictures and chartsMathVista+11.9points aheadQwen2.5 VL 72B74.8Gemma 3 12B62.9
  • College exam questions with charts, maps and diagramsMMMU+10.6points aheadQwen2.5 VL 72B70.2Gemma 3 12B59.6

Where Gemma 3 12B pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Images and chartsQwen2.5 VL 72B
  • MMMU-ProQwen2.5 VL 72B by 13.637.551.1+13.6
  • MathVistaQwen2.5 VL 72B by 11.962.974.8+11.9
  • MMMUQwen2.5 VL 72B by 10.659.670.2+10.6

Full images and charts ranking

Other results14 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.

Questions people ask

Which is better, Gemma 3 12B or Qwen2.5 VL 72B?

Qwen2.5 VL 72B wins the one area where both have results: images and charts. Gemma 3 12B wins none.

How do you compare the two?

We use the 17 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 14 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.