Gemma 4 E4B vs InternVL3_5-4B

Google · released Apr 3, 2026

Wins 1 of 2 areas

Following instructions

OpenGVLab

Wins 1 of 2 areas

Images and charts

The two are evenly matched.Gemma 4 E4B is better at following instructions; InternVL3_5-4B at images and charts.

Scores updated Sep 19, 2026 · 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.

Images and chartsUnderstanding pictures, charts and video13InternVL3_5-4B3 of 4 tests
Following instructionsDoing exactly what it is asked10Gemma 4 E4B1 of 1 test

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.

Gemma 4 E4B$0.02 to read · $0.10 to write$0.12Price from Artificial Analysis

InternVL3_5-4BNo current price is tracked.

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

Math problems shown in pictures and chartsMathVista+21.9points aheadInternVL3_5-4B67.1Gemma 4 E4B45.2
Questions that truly need the image to answerMMStar+12.6points aheadInternVL3_5-4B65.5Gemma 4 E4B52.9
Visual perception tasks people solve at a glanceBLINK+5points aheadInternVL3_5-4B57.2Gemma 4 E4B52.2

Where Gemma 4 E4B pulls ahead

Harder college exam questions with imagesMMMU-Pro+28.7points aheadGemma 4 E4B51.4InternVL3_5-4B22.7
Follows unfamiliar, precisely checkable instructionsIFBench+19.7points aheadGemma 4 E4B44.2InternVL3_5-4B24.5

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_5-4B

MMMU-ProGemma 4 E4B by 28.751.422.7+28.7
MathVistaInternVL3_5-4B by 21.945.267.1+21.9
MMStarInternVL3_5-4B by 12.652.965.5+12.6
BLINKInternVL3_5-4B by 552.257.2+5

Full images and charts ranking

Following instructionsGemma 4 E4B

IFBenchGemma 4 E4B by 19.744.224.5+19.7

Full following instructions ranking

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 52.587.935.4+52.5
ChartQA TestInternVL3_5-4B by 44.142.186.2+44.1
ScreenSpot-v2 DesktopInternVL3_5-4B by 36.245.882+36.2
ScreenSpot-v2 WebInternVL3_5-4B by 3547.682.6+35
ScreenSpot-v2 MobileInternVL3_5-4B by 27.560.387.8+27.5
InfographicVQA (val)InternVL3_5-4B by 1660.976.9+16
MM-IFEvalGemma 4 E4B by 13.768.254.5+13.7
MMEInternVL3_5-4B by 13.467.681+13.4
MMMU (val) (Pass@1)InternVL3_5-4B by 11.449.360.7+11.4
MMBenchInternVL3_5-4B by 9.571.681.1+9.5
OCRBench v1InternVL3_5-4B by 8.573.582+8.5
TextVQA-valInternVL3_5-4B by 8.56977.5+8.5
Multilingual MMBenchInternVL3_5-4B by 5.471.276.6+5.4
DocVQA-valInternVL3_5-4B by 4.487.491.8+4.4
RealWorldQAInternVL3_5-4B by 3.464.367.7+3.4
SimpleVQAInternVL3_5-4B by 3.330.433.7+3.3
HallusionBenchInternVL3_5-4B by 2.349.852.1+2.3
POPEInternVL3_5-4B by 286.988.9+2
MMMBInternVL3_5-4B by 1.180.481.5+1.1
Multilingual MMMBInternVL3_5-4B by 1.180.481.5+1.1
SEED-Bench (image)InternVL3_5-4B by 1.175.376.4+1.1
OCRBench v2_entie48.849.1tie

Questions people ask

Which is better, Gemma 4 E4B or InternVL3_5-4B?

Gemma 4 E4B and InternVL3_5-4B each win one of the two areas where both have results. Gemma 4 E4B wins following instructions; InternVL3_5-4B 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.