Qwen2.5 VL 32B Instruct vs Qwen3 VL 30B A3B Instruct

Alibaba · released Mar 21, 2025

Wins 0 of 3 areas

—

Alibaba · released Oct 3, 2025

Wins 3 of 3 areas

Agents · Reasoning · Images and charts

Qwen3 VL 30B A3B Instruct is the stronger all-rounder.

Scores updated Sep 11, 2026 · 15 tests both models report · How we compare

Where each one wins

Tests won in each of the three 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.

Images and chartsUnderstanding pictures, charts and video13Qwen3 VL 30B A3B Instruct3 of 4 tests
AgentsCarrying out multi-step tasks on its own01Qwen3 VL 30B A3B Instruct1 of 1 test
ReasoningHard problems that need careful thinking01Qwen3 VL 30B A3B Instruct1 of 1 test

Agents and reasoning 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.

Qwen2.5 VL 32B InstructNo current price is tracked.

Qwen3 VL 30B A3B Instruct$0.20 to read · $0.80 to write$1.00Price from Alibaba's own price page

The biggest differences

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

Where Qwen3 VL 30B A3B Instruct pulls ahead

Completes tasks by operating a computer desktopOSWorld-Verified+24.4points aheadQwen3 VL 30B A3B Instruct30.3Qwen2.5 VL 32B Instruct5.9
Graduate-level biology, physics and chemistry questionsGPQA Diamond+23.5points aheadQwen3 VL 30B A3B Instruct69.5Qwen2.5 VL 32B Instruct46
Harder college exam questions with imagesMMMU-Pro+12.6points aheadQwen3 VL 30B A3B Instruct62.1Qwen2.5 VL 32B Instruct49.5

Where Qwen2.5 VL 32B Instruct pulls ahead

Questions about short and long videosVideo-MME+3.4points aheadQwen2.5 VL 32B Instruct77.9Qwen3 VL 30B A3B Instruct74.5

Every test, side by side

All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.

AgentsQwen3 VL 30B A3B Instruct

OSWorld-VerifiedQwen3 VL 30B A3B Instruct by 24.45.930.3+24.4

Full agents ranking

ReasoningQwen3 VL 30B A3B Instruct

GPQA DiamondQwen3 VL 30B A3B Instruct by 23.54669.5+23.5

Full reasoning ranking

Images and chartsQwen3 VL 30B A3B Instruct

MMMU-ProQwen3 VL 30B A3B Instruct by 12.649.562.1+12.6
MathVistaQwen3 VL 30B A3B Instruct by 5.474.780.1+5.4
Video-MMEQwen2.5 VL 32B Instruct by 3.477.974.5+3.4
MMStarQwen3 VL 30B A3B Instruct by 2.669.572.1+2.6

Full images and charts ranking

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.

MATH-VisionQwen3 VL 30B A3B Instruct by 21.838.460.2+21.8
ScreenSpot-Pro (No tools)Qwen3 VL 30B A3B Instruct by 21.139.460.5+21.1
LVBenchQwen3 VL 30B A3B Instruct by 13.54962.5+13.5
CharadesSTAQwen3 VL 30B A3B Instruct by 9.354.263.5+9.3
MMLU-ProQwen3 VL 30B A3B Instruct by 968.877.8+9
ScreenSpotQwen3 VL 30B A3B Instruct by 6.288.594.7+6.2
OCRBench v2_enQwen3 VL 30B A3B Instruct by 657.263.2+6
CC-OCRQwen3 VL 30B A3B Instruct by 3.677.180.7+3.6
OCRBench v2 (Chinese)Qwen2.5 VL 32B Instruct by 1.359.157.8+1.3

Questions people ask

Which is better, Qwen2.5 VL 32B Instruct or Qwen3 VL 30B A3B Instruct?

Qwen3 VL 30B A3B Instruct wins all three areas where both have results: agents, reasoning and images and charts. Qwen2.5 VL 32B Instruct wins none.

How do you compare the two?

We use the 15 benchmark tests both models have published scores on. The verdict counts the 6 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.