Gemma 4 E2B vs InternVL3_5-4B
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; InternVL3_5-4B at images and charts.
Scores updated · 28 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 InternVL3_5-4B pulls ahead
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsInternVL3_5-4B
Following instructionsGemma 4 E2B
- IFBenchGemma 4 E2B by 13.53824.5+13.5
Other results23 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 WebInternVL3_5-4B by 60.222.482.6+60.2
- ScreenSpot-v2 DesktopInternVL3_5-4B by 53.928.182+53.9
- IFEvalGemma 4 E2B by 47.68335.4+47.6
- ScreenSpot-v2 MobileInternVL3_5-4B by 44.942.987.8+44.9
- ChartQA TestInternVL3_5-4B by 4343.286.2+43
- MMEInternVL3_5-4B by 26.154.981+26.1
- InfographicVQA (val)InternVL3_5-4B by 22.554.476.9+22.5
- MMMU (val) (Pass@1)InternVL3_5-4B by 19.641.160.7+19.6
- TextVQA-valInternVL3_5-4B by 1562.577.5+15
- MMBenchInternVL3_5-4B by 13.862.876.6+13.8
- Multilingual MMBenchInternVL3_5-4B by 13.862.876.6+13.8
- OCRBench v1InternVL3_5-4B by 11.870.282+11.8
- MM-IFEvalGemma 4 E2B by 11.165.654.5+11.1
- Multilingual MMMBInternVL3_5-4B by 8.273.381.5+8.2
- HallusionBenchGemma 4 E2B by 7.759.852.1+7.7
- RealWorldQAInternVL3_5-4B by 7.76067.7+7.7
- MMMBInternVL3_5-4B by 7.274.381.5+7.2
- SimpleVQAInternVL3_5-4B by 6.427.333.7+6.4
- DocVQA-valInternVL3_5-4B by 6.185.791.8+6.1
- VLM Judge ScoreInternVL3_5-4B by 5.884.490.2+5.8
- OCRBench v2_enInternVL3_5-4B by 5.643.549.1+5.6
- SEED-Bench (image)InternVL3_5-4B by 571.476.4+5
- POPEInternVL3_5-4B by 4.98488.9+4.9
Questions people ask
Which is better, Gemma 4 E2B or InternVL3_5-4B?
Gemma 4 E2B and InternVL3_5-4B each win one of the two areas where both have results. Gemma 4 E2B wins following instructions; InternVL3_5-4B wins images and charts.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 23 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.