Gemma 4 E4B vs InternVL3_5-2B
Wins 1 of 2 areas
Following instructions
Wins 1 of 2 areas
Images and charts
The two are evenly matched.Gemma 4 E4B is better at following instructions; InternVL3_5-2B at images and charts.
Scores updated · 27 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.
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
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsInternVL3_5-2B
Following instructionsGemma 4 E4B
- IFBenchGemma 4 E4B by 19.844.224.4+19.8
Other results22 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.
- IFEvalGemma 4 E4B by 55.587.932.4+55.5
- ChartQA TestInternVL3_5-2B by 39.642.181.7+39.6
- ScreenSpot-v2 DesktopInternVL3_5-2B by 34.145.879.9+34.1
- ScreenSpot-v2 WebInternVL3_5-2B by 32.347.679.9+32.3
- ScreenSpot-v2 MobileInternVL3_5-2B by 25.960.386.2+25.9
- MM-IFEvalGemma 4 E4B by 21.168.247.1+21.1
- OCRBench v1InternVL3_5-2B by 10.473.583.9+10.4
- InfographicVQA (val)InternVL3_5-2B by 8.460.969.3+8.4
- TextVQA-valInternVL3_5-2B by 7.66976.6+7.6
- MMEInternVL3_5-2B by 667.673.6+6
- MMBenchInternVL3_5-2B by 4.671.676.2+4.6
- MMMBGemma 4 E4B by 4.180.476.3+4.1
- Multilingual MMMBGemma 4 E4B by 4.180.476.3+4.1
- OCRBench v2_enGemma 4 E4B by 3.348.845.5+3.3
- MMMU (val) (Pass@1)InternVL3_5-2B by 2.749.352+2.7
- RealWorldQAGemma 4 E4B by 2.764.361.6+2.7
- HallusionBenchGemma 4 E4B by 2.249.847.6+2.2
- POPEInternVL3_5-2B by 1.186.988+1.1
- DocVQA-valInternVL3_5-2B by 187.488.4+1
- Multilingual MMBenchtie71.270.9tie
- SEED-Bench (image)tie75.375.4tie
- SimpleVQAtie30.430.5tie
Questions people ask
Which is better, Gemma 4 E4B or InternVL3_5-2B?
Gemma 4 E4B and InternVL3_5-2B each win one of the two areas where both have results. Gemma 4 E4B wins following instructions; InternVL3_5-2B wins images and charts.
How do you compare the two?
We use the 27 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 22 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.