Mage-VL-4B vs Phi 4 R V 15B

Microsoft · released Jul 26, 2026

Wins 1 of 1 area

Images and charts

Microsoft · released Mar 4, 2026

Wins 0 of 1 area

—

Mage-VL-4B is the stronger all-rounder.

Scores updated Jul 26, 2026 · 25 tests both models report · How we compare

Where each one wins

Tests won in each of the one area 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 video40Mage-VL-4B4 of 4 tests

The biggest differences

The tests each model wins by the widest margin, up to three each. Scores are out of 100.

Where Mage-VL-4B pulls ahead

Questions about short and long videosVideo-MME+8.7points aheadMage-VL-4B64Phi 4 R V 15B55.3
Reads text in imagesOCRBench+7.9points aheadMage-VL-4B81.8Phi 4 R V 15B73.9
Questions that truly need the image to answerMMStar+7.7points aheadMage-VL-4B67.3Phi 4 R V 15B59.6

Where Phi 4 R V 15B pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Images and chartsMage-VL-4B

Video-MMEMage-VL-4B by 8.76455.3+8.7
OCRBenchMage-VL-4B by 7.981.873.9+7.9
MMStarMage-VL-4B by 7.767.359.6+7.7
BLINKMage-VL-4B by 7.365.157.8+7.3

Full images and charts ranking

Other results21 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.

VSI-BenchMage-VL-4B by 38.864.325.5+38.8
MultiDocVQA-valMage-VL-4B by 29.187.558.4+29.1
InfoVQA (val)Mage-VL-4B by 24.980.355.4+24.9
Ref-DAVIS17Mage-VL-4B by 23.625.82.1+23.6
Timelens-ActivityNetMage-VL-4B by 22.445.423+22.4
DocVQA-valMage-VL-4B by 18.995.176.2+18.9
MLVU-devMage-VL-4B by 16.968.751.8+16.9
MV-BenchMage-VL-4B by 15.965.149.2+15.9
NextQAMage-VL-4B by 14.183.169+14.1
MME-PerceptionMage-VL-4B by 120 rating points17101590+120 rating
LongVideoBenchMage-VL-4B by 10.161.351.2+10.1
MME-RealWorldMage-VL-4B by 8.766.557.8+8.7
LVBenchMage-VL-4B by 7.441.834.4+7.4
ChartQAProMage-VL-4B by 7.232.625.4+7.2
CV-BenchMage-VL-4B by 6.587.881.3+6.5
MMBench-CN-devMage-VL-4B by 2.58279.5+2.5
ChartQAMage-VL-4B by 1.584.983.4+1.5
TextVQA-valMage-VL-4B by 1.277.376.1+1.2
SATtie67.366.7tie
AI2D w/ Masktie83.282.9tie
MMBench-EN-devtie8484.2tie

Questions people ask

Which is better, Mage-VL-4B or Phi 4 R V 15B?

Mage-VL-4B wins the one area where both have results: images and charts. Phi 4 R V 15B wins none.

How do you compare the two?

We use the 25 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 21 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.