Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

InternVL3_5-2B vs LFM2-VL-450M

OpenGVLab

Wins 1 of 1 area

Images and charts

Liquid AI · released

Wins 0 of 1 area

—

InternVL3_5-2B 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 InternVL3_5-2B pulls ahead

  • Reads text in imagesOCRBench+17.7points aheadInternVL3_5-2B83.4LFM2-VL-450M65.7
  • Questions that truly need the image to answerMMStar+16.8points aheadInternVL3_5-2B57.7LFM2-VL-450M40.9
  • Math problems shown in pictures and chartsMathVista+11.5points aheadInternVL3_5-2B56.8LFM2-VL-450M45.3

Where LFM2-VL-450M pulls ahead

No clear win on a test scored out of 100.

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 chartsInternVL3_5-2B
  • OCRBenchInternVL3_5-2B by 17.783.465.7+17.7
  • MMStarInternVL3_5-2B by 16.857.740.9+16.8
  • MathVistaInternVL3_5-2B by 11.556.845.3+11.5
  • BLINKInternVL3_5-2B by 9.45242.6+9.4

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, InternVL3_5-2B or LFM2-VL-450M?

InternVL3_5-2B 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.