Qwen3.5 35B A3B is the stronger all-rounder.GLM-4.6V-Flash (9B) is cheaper.
Scores updated · 9 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.
GLM-4.6V-Flash (9B) costs 47% 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 Qwen3.5 35B A3B pulls ahead
- College exam questions with charts, maps and diagramsMMMU+10.2points ahead
- Questions that truly need the image to answerMMStar+7.6points ahead
- Reads and reasons about text in imagesOCRBenchv2+6.3points ahead
Where GLM-4.6V-Flash (9B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 9 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsQwen3.5 35B A3B
- MMMUQwen3.5 35B A3B by 10.271.281.4+10.2
- MMStarQwen3.5 35B A3B by 7.674.381.9+7.6
- OCRBenchv2Qwen3.5 35B A3B by 6.35965.3+6.3
- OCRBenchQwen3.5 35B A3B by 58691+5
- MathVistaQwen3.5 35B A3B by 3.382.886.2+3.3
Other results4 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-VisionQwen3.5 35B A3B by 29.85483.9+29.8
- ScreenSpot-Pro (No tools)Qwen3.5 35B A3B by 22.945.768.6+22.9
- AI2DQwen3.5 35B A3B by 3.788.992.6+3.7
- OCRBench v2 (Chinese)Qwen3.5 35B A3B by 2.259.561.7+2.2
Questions people ask
Which is better, GLM-4.6V-Flash (9B) or Qwen3.5 35B A3B?
Qwen3.5 35B A3B wins the one area where both have results: images and charts. GLM-4.6V-Flash (9B) wins none, but costs 47% less.
Which is cheaper?
GLM-4.6V-Flash (9B) costs $0.30 per million input tokens and $0.90 per million output tokens; Qwen3.5 35B A3B costs $0.25 and $2.00. That makes GLM-4.6V-Flash (9B) about 47% cheaper for the same work.
How do you compare the two?
We use the 9 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.