Gemma 4 E4B 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 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.
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 Gemma 4 E4B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+34.5points ahead
- Questions that truly need the image to answerMMStar+12points ahead
- Visual perception tasks people solve at a glanceBLINK+9.6points ahead
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 chartsGemma 4 E4B
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.
- MMLU-ProGemma 4 E4B by 52.269.417.2+52.2
- IFEvalGemma 4 E4B by 36.187.951.8+36.1
- MM-IFEvalGemma 4 E4B by 35.168.233.1+35.1
- MMMBGemma 4 E4B by 26.180.454.3+26.1
- MMMU (val) (Pass@1)Gemma 4 E4B by 14.949.334.4+14.9
- RealWorldQAGemma 4 E4B by 12.364.352+12.3
- POPEGemma 4 E4B by 3.186.983.8+3.1
Questions people ask
Which is better, Gemma 4 E4B or LFM2-VL-450M?
Gemma 4 E4B wins all two areas where both have results: reasoning and 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.