Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d254Policy30d64, 14 pendingSources1,010

GLM-4.6V (106B-A12B) vs Seed-1.5-VL

Z.ai

Wins 0 of 1 area

—

ByteDance

Wins 1 of 1 area

Images and charts

Seed-1.5-VL is the stronger all-rounder.

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.

The biggest differences

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

Where Seed-1.5-VL pulls ahead

  • College exam questions with charts, maps and diagramsMMMU+3.9points aheadSeed-1.5-VL79.1GLM-4.6V (106B-A12B)75.2
  • Questions that truly need the image to answerMMStar+2.6points aheadSeed-1.5-VL77.9GLM-4.6V (106B-A12B)75.3
  • Math problems shown in pictures and chartsMathVista+2.1points aheadSeed-1.5-VL85.6GLM-4.6V (106B-A12B)83.5

Where GLM-4.6V (106B-A12B) pulls ahead

  • Reads text in imagesOCRBench+1points aheadGLM-4.6V (106B-A12B)86.2Seed-1.5-VL85.2

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 chartsSeed-1.5-VL
  • MMMUSeed-1.5-VL by 3.975.279.1+3.9
  • MMStarSeed-1.5-VL by 2.675.377.9+2.6
  • MathVistaSeed-1.5-VL by 2.183.585.6+2.1
  • OCRBenchGLM-4.6V (106B-A12B) by 186.285.2+1

Full images and charts ranking

Other results5 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, GLM-4.6V (106B-A12B) or Seed-1.5-VL?

Seed-1.5-VL wins the one area where both have results: images and charts. GLM-4.6V (106B-A12B) wins none.

How do you compare the two?

We use the 9 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.