Gemma 3 4B wins more areas, narrowly.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- ReasoningHard problems that need careful thinking10Gemma 3 4B1 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked10Gemma 3 4B1 of 1 test
- CodingWriting and fixing software00Even0 each · 2 ties
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, long documents 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
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.1points ahead
Where Granite 4.0 H 1B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+16.5points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningGemma 3 4B
- GPQA DiamondGemma 3 4B by 2.829.126.3+2.8
- Humanity's Last Examtie5.35tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.0 H 1B by 16.51.818.3+16.5
- AA-Omniscience · AccuracyGemma 3 4B by 2.57.75.2+2.5
Following instructionsGemma 3 4B
- IFBenchGemma 3 4B by 2.128.326.2+2.1
Other results9 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 2673.247.2+26
- GSM8KGemma 3 4B by 19.689.269.6+19.6
- MMLU-ProGemma 3 4B by 1643.627.6+16
- τ²-Bench Telecom (AA run)Granite 4.0 H 1B by 14.6519.6+14.6
- AA-OmniscienceGranite 4.0 H 1B by 10.6-82.9-72.3+10.6
- IFEvalGemma 3 4B by 10.190.280.1+10.1
- AA Agentic IndexGranite 4.0 H 1B by 4.81.76.5+4.8
- AA Intelligencetie4.85.2tie
- Artificial Analysis Coding Indextie2.72.7tie
Questions people ask
Which is better, Gemma 3 4B or Granite 4.0 H 1B?
Gemma 3 4B wins two of the six areas where both have results: reasoning and following instructions. Granite 4.0 H 1B wins none. They are level on coding, agents, facts and long documents.
Which is better for coding?
Neither. All 2 coding tests both models report are ties.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.