Gemma 3 4B vs Gemma 4 26B A4B
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Gemma 4 26B A4B is the stronger all-rounder.Gemma 3 4B is cheaper.
Scores updated · 31 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- CodingWriting and fixing software03Gemma 4 26B A4B3 of 3 tests
- FactsGetting facts right instead of making them up03Gemma 4 26B A4B3 of 3 tests
- ReasoningHard problems that need careful thinking02Gemma 4 26B A4B2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own02Gemma 4 26B A4B2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video02Gemma 4 26B A4B2 of 2 tests
- Long documentsFinding answers in very long texts01Gemma 4 26B A4B1 of 1 test
- Following instructionsDoing exactly what it is asked01Gemma 4 26B A4B1 of 1 test
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.
Gemma 3 4B costs 72% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemma 4 26B A4B pulls ahead
- Reasons across sets of long documentsAA-LCR+59points ahead
- Recent programming contest problemsLiveCodeBench v6+58.2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+50.1points ahead
Where Gemma 3 4B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 26B A4B
- LiveCodeBench v6Gemma 4 26B A4B by 58.218.977.1+58.2
- SciCodeGemma 4 26B A4B by 32.77.340+32.7
- Terminal-Bench HardGemma 4 26B A4B by 12.80.813.6+12.8
AgentsGemma 4 26B A4B
- τ-Bench V3 · BankingGemma 4 26B A4B by 11.60.412+11.6
- GDPValGemma 4 26B A4B by 3.403.4+3.4
ReasoningGemma 4 26B A4B
- GPQA DiamondGemma 4 26B A4B by 50.129.179.2+50.1
- Humanity's Last ExamGemma 4 26B A4B by 145.319.3+14
- CritPttie00tie
FactsGemma 4 26B A4B
- AA-Omniscience · Non-hallucinationGemma 4 26B A4B by 11.81.813.6+11.8
- AA-Omniscience · AccuracyGemma 4 26B A4B by 11.47.719.1+11.4
- Vectara HHEM hallucination ratelower is betterGemma 4 26B A4B by 1.26.45.2+1.2
Images and chartsGemma 4 26B A4B
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 44.128.372.4+44.1
Other results16 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.
- BIG-Bench Extra HardGemma 4 26B A4B by 53.81164.8+53.8
- MMLU-ProGemma 4 26B A4B by 3943.682.6+39
- τ²-Bench Telecom (AA run)Gemma 4 26B A4B by 38.6543.6+38.6
- Artificial Analysis Coding IndexGemma 4 26B A4B by 36.62.739.3+36.6
- MMMLUGemma 4 26B A4B by 36.250.186.3+36.2
- vectara_answer_rateGemma 4 26B A4B by 32.567.399.8+32.5
- AA-OmniscienceGemma 4 26B A4B by 32.1-82.9-50.8+32.1
- HumanEvalGemma 3 4B by 21.371.350+21.3
- MMLUGemma 4 26B A4B by 19.458.477.8+19.4
- AI2DGemma 4 26B A4B by 13.574.888.3+13.5
- AA IntelligenceGemma 4 26B A4B by 11.94.816.7+11.9
- vectara_avg_summary_lengthGemma 3 4B by 10.377.467.1+10.3
- AA Agentic IndexGemma 4 26B A4B by 9.31.711+9.3
- MBPPGemma 4 26B A4B by 5.263.268.4+5.2
- IFEvalGemma 4 26B A4B by 1.290.291.4+1.2
- vectara_factual_consistencyGemma 4 26B A4B by 1.293.694.8+1.2
Questions people ask
Which is better, Gemma 3 4B or Gemma 4 26B A4B?
Gemma 4 26B A4B wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Gemma 3 4B wins none, but costs 72% less.
Which is better for coding?
Gemma 4 26B A4B. It wins 3 of the 3 coding tests both models report; Gemma 3 4B wins none.
Which is cheaper?
Gemma 3 4B costs $0.05 per million input tokens and $0.10 per million output tokens; Gemma 4 26B A4B costs $0.13 and $0.40. That makes Gemma 3 4B about 72% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.