Gemma 4 E2B vs LFM2.5-VL-450M-Extract
Wins 2 of 2 areas
Reasoning · Images and charts
Wins 0 of 2 areas
—
Gemma 4 E2B is the stronger all-rounder.
Scores updated · 13 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.
Reasoning 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 Gemma 4 E2B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+17.6points ahead
- Reads text in imagesOCRBench+3.5points ahead
- Questions that truly need the image to answerMMStar+2.3points ahead
Where LFM2.5-VL-450M-Extract pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsGemma 4 E2B
Other results9 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.
- MMLU-ProGemma 4 E2B by 40.76019.3+40.7
- IFEvalGemma 4 E2B by 21.88361.2+21.8
- MM-IFEvalGemma 4 E2B by 20.665.645+20.6
- BFCLv4Gemma 4 E2B by 12.133.221.1+12.1
- VLM Judge ScoreGemma 4 E2B by 1184.473.4+11
- MMMU (val) (Pass@1)Gemma 4 E2B by 8.441.132.7+8.4
- MMMBGemma 4 E2B by 6.274.368.1+6.2
- POPELFM2.5-VL-450M-Extract by 2.98486.9+2.9
- RealWorldQAGemma 4 E2B by 1.66058.4+1.6
Questions people ask
Which is better, Gemma 4 E2B or LFM2.5-VL-450M-Extract?
Gemma 4 E2B wins all two areas where both have results: reasoning and images and charts. LFM2.5-VL-450M-Extract wins none.
How do you compare the two?
We use the 13 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 9 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.