LFM3-VL-2B is the stronger all-rounder.
Scores updated · 24 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LFM3-VL-2B pulls ahead
Where Gemma 4 E4B pulls ahead
- Harder college exam questions with imagesMMMU-Pro+5.7points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsLFM3-VL-2B
Other results20 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.
- ChartQA TestLFM3-VL-2B by 50.642.192.7+50.6
- ScreenSpot-v2 DesktopLFM3-VL-2B by 48.845.894.6+48.8
- ScreenSpot-v2 WebLFM3-VL-2B by 42.347.689.9+42.3
- ScreenSpot-v2 MobileLFM3-VL-2B by 31.960.392.2+31.9
- InfographicVQA (val)LFM3-VL-2B by 25.360.986.2+25.3
- MMELFM3-VL-2B by 19.367.686.9+19.3
- TextVQA-valLFM3-VL-2B by 18.96987.9+18.9
- HallusionBenchLFM3-VL-2B by 15.849.865.6+15.8
- RealWorldQALFM3-VL-2B by 1564.379.3+15
- OCRBench v2_enLFM3-VL-2B by 14.748.863.5+14.7
- MMBenchLFM3-VL-2B by 14.571.686.1+14.5
- OCRBench v1LFM3-VL-2B by 12.873.586.3+12.8
- Multilingual MMBenchLFM3-VL-2B by 12.471.283.6+12.4
- DocVQA-valLFM3-VL-2B by 9.387.496.7+9.3
- MMMU (val) (Pass@1)LFM3-VL-2B by 6.449.355.7+6.4
- SimpleVQALFM3-VL-2B by 5.930.436.3+5.9
- MMMBLFM3-VL-2B by 4.880.485.2+4.8
- MM-IFEvalLFM3-VL-2B by 4.668.272.8+4.6
- SEED-Bench (image)LFM3-VL-2B by 3.375.378.6+3.3
- POPELFM3-VL-2B by 1.886.988.7+1.8
Questions people ask
Which is better, Gemma 4 E4B or LFM3-VL-2B?
LFM3-VL-2B wins the one area where both have results: images and charts. Gemma 4 E4B wins none.
How do you compare the two?
We use the 24 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 20 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.