Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

LFM2-VL-1.6B vs LFM2-VL-450M

Liquid AI · released

Wins 1 of 1 area

Images and charts

Liquid AI · released

Wins 0 of 1 area

—

LFM2-VL-1.6B is the stronger all-rounder.

Scores updated · 11 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 LFM2-VL-1.6B pulls ahead

  • Questions that truly need the image to answerMMStar+9points aheadLFM2-VL-1.6B49.9LFM2-VL-450M40.9
  • Math problems shown in pictures and chartsMathVista+6.4points aheadLFM2-VL-1.6B51.7LFM2-VL-450M45.3
  • Visual perception tasks people solve at a glanceBLINK+1.9points aheadLFM2-VL-1.6B44.5LFM2-VL-450M42.6

Where LFM2-VL-450M pulls ahead

  • Reads text in imagesOCRBench+30.6points aheadLFM2-VL-450M65.7LFM2-VL-1.6B35.1

Every test, side by side

All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Images and chartsLFM2-VL-1.6B
  • OCRBenchLFM2-VL-450M by 30.635.165.7+30.6
  • MMStarLFM2-VL-1.6B by 949.940.9+9
  • MathVistaLFM2-VL-1.6B by 6.451.745.3+6.4
  • BLINKLFM2-VL-1.6B by 1.944.542.6+1.9

Full images and charts ranking

Other results7 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, LFM2-VL-1.6B or LFM2-VL-450M?

LFM2-VL-1.6B wins the one area where both have results: images and charts. LFM2-VL-450M wins none.

How do you compare the two?

We use the 11 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 7 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.