Gemma 4 E2B vs LFM2.5-VL-3B
Wins 1 of 2 areas
Following instructions
Wins 1 of 2 areas
Images and charts
The two are evenly matched.Gemma 4 E2B is better at following instructions; LFM2.5-VL-3B at images and charts.
Scores updated · 33 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas 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.
Following instructions rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LFM2.5-VL-3B pulls ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsLFM2.5-VL-3B
Following instructionsGemma 4 E2B
- IFBenchGemma 4 E2B by 12.23825.8+12.2
Other results26 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.
- ScreenSpot-v2 WebLFM2.5-VL-3B by 59.822.482.2+59.8
- ScreenSpot-v2 DesktopLFM2.5-VL-3B by 50.628.178.7+50.6
- ScreenSpot-v2 (avg)LFM2.5-VL-3B by 49.631.180.7+49.6
- ScreenSpot-v2 MobileLFM2.5-VL-3B by 38.342.981.2+38.3
- ChartQA TestLFM2.5-VL-3B by 38.143.281.3+38.1
- ChartQALFM2.5-VL-3B by 37.843.581.3+37.8
- TextVQA-valLFM2.5-VL-3B by 21.862.584.3+21.8
- RefCOCO (Macro Prec@1)LFM2.5-VL-3B by 20.667.387.9+20.6
- MMELFM2.5-VL-3B by 18.254.973.1+18.2
- MMBenchLFM2.5-VL-3B by 16.864.281+16.8
- Multilingual MMBenchLFM2.5-VL-3B by 16.762.879.5+16.7
- InfographicVQA (val)LFM2.5-VL-3B by 15.854.470.2+15.8
- OCRBench v1LFM2.5-VL-3B by 1470.284.2+14
- RealWorldQALFM2.5-VL-3B by 13.16073.1+13.1
- HallusionBenchGemma 4 E2B by 12.659.847.2+12.6
- Multilingual MMMBLFM2.5-VL-3B by 9.773.383+9.7
- MMMBLFM2.5-VL-3B by 8.774.383+8.7
- SimpleVQALFM2.5-VL-3B by 8.127.335.4+8.1
- MMMU (val) (Pass@1)LFM2.5-VL-3B by 7.341.148.4+7.3
- SEED-Bench (image)LFM2.5-VL-3B by 6.371.477.7+6.3
- DocVQA-valLFM2.5-VL-3B by 5.485.791.1+5.4
- MM-IFEvalGemma 4 E2B by 565.660.6+5
- POPELFM2.5-VL-3B by 4.78488.7+4.7
- OCRBench v2_enLFM2.5-VL-3B by 443.547.5+4
- BFCLv4tie33.232.5tie
- IFEvaltie8382.3tie
Questions people ask
Which is better, Gemma 4 E2B or LFM2.5-VL-3B?
Gemma 4 E2B and LFM2.5-VL-3B each win one of the two areas where both have results. Gemma 4 E2B wins following instructions; LFM2.5-VL-3B wins images and charts.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 7 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 26 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.