Gemma 3 4B vs Granite 4.0 H Tiny
Wins 2 of 3 areas
Reasoning · Following instructions
Wins 1 of 3 areas
Coding
Gemma 3 4B is the stronger all-rounder.Granite 4.0 H Tiny is better at coding.
Scores updated · 13 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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.
Coding, reasoning and following instructions rest on a single test each.
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 3 4B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+9.9points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.6points ahead
Where Granite 4.0 H Tiny pulls ahead
- Recent programming contest problemsLiveCodeBench v6+7.8points ahead
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Following instructionsGemma 3 4B
- IFBenchGemma 3 4B by 9.928.318.4+9.9
Other results10 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.
- MATH-500 (EM)Gemma 3 4B by 1573.258.2+15
- MGSMGemma 3 4B by 13.687.373.7+13.6
- MMLU-ProGemma 3 4B by 11.643.632+11.6
- HumanEval+Granite 4.0 H Tiny by 1162.873.8+11
- GSMPlusGemma 3 4B by 9.368.459.1+9.3
- IFEvalGemma 3 4B by 9.190.281.1+9.1
- MMLUGranite 4.0 H Tiny by 8.458.466.8+8.4
- LCB v5Granite 4.0 H Tiny by 8.219.127.3+8.2
- GSM8KGemma 3 4B by 6.689.282.6+6.6
- MMMLUGranite 4.0 H Tiny by 650.156.1+6
Questions people ask
Which is better, Gemma 3 4B or Granite 4.0 H Tiny?
Gemma 3 4B wins two of the three areas where both have results: reasoning and following instructions. Granite 4.0 H Tiny wins coding.
Which is better for coding?
Granite 4.0 H Tiny. It wins the one coding test both models report.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.