Gemma 3 1B Instruct vs Gemma 3 27B
Wins 0 of 5 areas
—
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Gemma 3 27B is the stronger all-rounder.
Scores updated · 25 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 software02Gemma 3 27B2 of 2 tests
- ReasoningHard problems that need careful thinking01Gemma 3 27B1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Gemma 3 27B1 of 1 test
- Following instructionsDoing exactly what it is asked01Gemma 3 27B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 27B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+24.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+19.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.9points ahead
Where Gemma 3 1B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.8points ahead
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.
CodingGemma 3 27B
- LiveCodeBench v6Gemma 3 27B by 24.84.329.1+24.8
- Terminal-Bench HardGemma 3 27B by 3.803.8+3.8
ReasoningGemma 3 27B
- GPQA DiamondGemma 3 27B by 19.123.742.8+19.1
- Humanity's Last Examtie5.34.4tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 3 1B Instruct by 9.817.77.9+9.8
- AA-Omniscience · AccuracyGemma 3 27B by 9.23.812.9+9.2
Following instructionsGemma 3 27B
- IFBenchGemma 3 27B by 11.919.931.8+11.9
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.
- MMLU-ProGemma 3 27B by 52.914.767.6+52.9
- BBHGemma 3 27B by 48.539.187.6+48.5
- HumanEvalGemma 3 27B by 46.341.587.8+46.3
- Global-MMLU-LiteGemma 3 27B by 40.934.275.1+40.9
- MBPPGemma 3 27B by 39.235.274.4+39.2
- MMLUGemma 3 27B by 36.840.176.9+36.8
- MMMLUGemma 3 27B by 36.334.470.7+36.3
- GSM8KGemma 3 27B by 33.162.895.9+33.1
- LiveCodeBenchGemma 3 27B by 27.81.929.7+27.8
- BIG-Bench Extra HardGemma 3 27B by 12.17.219.3+12.1
- IFEvalGemma 3 27B by 10.280.290.4+10.2
- AA-OmniscienceGemma 3 27B by 8.2-75.5-67.2+8.2
- SimpleQAGemma 3 27B by 7.82.210+7.8
- τ²-BenchGemma 3 27B by 6.89.416.2+6.8
- AA Intelligencetie4.84.9tie
- τ²-Bench Telecom (AA run)tie10.510.5tie
Questions people ask
Which is better, Gemma 3 1B Instruct or Gemma 3 27B?
Gemma 3 27B wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Gemma 3 1B Instruct wins none. They are level on facts.
Which is better for coding?
Gemma 3 27B. It wins 2 of the 2 coding tests both models report; Gemma 3 1B Instruct wins none.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 9 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.