Gemini 3.1 Pro vs Gemma 3 27B
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Gemini 3.1 Pro is the stronger all-rounder.Gemma 3 27B is cheaper.
Scores updated · 34 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 software50Gemini 3.1 Pro5 of 5 tests
- AgentsCarrying out multi-step tasks on its own30Gemini 3.1 Pro3 of 3 tests
- ReasoningHard problems that need careful thinking30Gemini 3.1 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30Gemini 3.1 Pro3 of 3 tests
- Long documentsFinding answers in very long texts20Gemini 3.1 Pro2 of 2 tests
- FactsGetting facts right instead of making them up21Gemini 3.1 Pro2 of 3 tests
- MathCompetition and research-level math10Gemini 3.1 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 of 1 test
Math 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 27B costs 98% 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 Gemini 3.1 Pro pulls ahead
- US invitational high-school math exam problemsAIME 2026+77.5points ahead
- Reasons across sets of long documentsAA-LCR+74.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+69.3points ahead
Where Gemma 3 27B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- Terminal-Bench 2.1Gemini 3.1 Pro by 69.373.84.5+69.3
- LiveCodeBench v6Gemini 3.1 Pro by 62.691.729.1+62.6
- Terminal-Bench HardGemini 3.1 Pro by 5053.83.8+50
- SWE-bench ProGemini 3.1 Pro by 42.854.211.4+42.8
- SciCodeGemini 3.1 Pro by 35.458.723.3+35.4
AgentsGemini 3.1 Pro
- τ-Bench V3 · BankingGemini 3.1 Pro by 20.621.40.8+20.6
- GDPValGemini 3.1 Pro by 14.714.70+14.7
- Terminal-Bench 4.0Gemini 3.1 Pro by 440+4
ReasoningGemini 3.1 Pro
- GPQA DiamondGemini 3.1 Pro by 51.394.142.8+51.3
- Humanity's Last ExamGemini 3.1 Pro by 42.6474.4+42.6
- CritPtGemini 3.1 Pro by 17.717.70+17.7
FactsGemini 3.1 Pro
- AA-Omniscience · AccuracyGemini 3.1 Pro by 41.954.912.9+41.9
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 41.249.17.9+41.2
- Vectara HHEM hallucination ratelower is betterGemma 3 27B by 310.47.4+3
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 34.482.448+34.4
- MathVistaGemini 3.1 Pro by 22.690.267.6+22.6
- LMArena · VisionGemini 3.1 Pro by 132 rating points12961164+132 rating
Long documentsGemini 3.1 Pro
- AA-LCRGemini 3.1 Pro by 74.7827.3+74.7
- MRCR v2 8 needle 128k (average)Gemini 3.1 Pro by 12.826.313.5+12.8
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 45.377.131.8+45.3
Other results13 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.
- AA-OmniscienceGemini 3.1 Pro by 99.131.9-67.2+99.1
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 85.195.610.5+85.1
- LiveCodeBenchGemini 3.1 Pro by 6291.729.7+62
- Artificial Analysis Coding IndexGemini 3.1 Pro by 58.768.810.1+58.7
- MATH-VisionGemini 3.1 Pro by 43.889.846+43.8
- AA IntelligenceGemini 3.1 Pro by 24.829.74.9+24.8
- MMLU-ProGemini 3.1 Pro by 23.49167.6+23.4
- MMMLUGemini 3.1 Pro by 21.992.670.7+21.9
- Global-MMLU-LiteGemini 3.1 Pro by 17.692.775.1+17.6
- MMLUGemini 3.1 Pro by 15.792.676.9+15.7
- vectara_factual_consistencyGemma 3 27B by 389.692.6+3
- vectara_avg_summary_lengthGemini 3.1 Pro by 11.3 rating points107.796.4+11.3 rating
- vectara_answer_ratetie99.498.8tie
Questions people ask
Which is better, Gemini 3.1 Pro or Gemma 3 27B?
Gemini 3.1 Pro wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Gemma 3 27B wins none, but costs 98% less.
Which is better for coding?
Gemini 3.1 Pro. It wins 5 of the 5 coding tests both models report; Gemma 3 27B wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Gemma 3 27B costs $0.08 and $0.16. That makes Gemma 3 27B about 98% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.