Gemini 3.1 Pro vs Gemma 4 12B
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 0 of 8 areas
—
Gemini 3.1 Pro is the stronger all-rounder.Gemma 4 12B is cheaper.
Scores updated · 26 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 software40Gemini 3.1 Pro4 of 4 tests
- ReasoningHard problems that need careful thinking30Gemini 3.1 Pro3 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Gemini 3.1 Pro2 of 2 tests
- FactsGetting facts right instead of making them up20Gemini 3.1 Pro2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3.1 Pro2 of 2 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
- Long documentsFinding answers in very long texts11Even1 each
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 4 12B costs 97% 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
- Command-line tasks in a real terminalTerminal-Bench 2.1+46.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+39.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+35.6points ahead
Where Gemma 4 12B pulls ahead
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+17.1points ahead
Every test, side by side
All 26 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 46.573.827.3+46.5
- Terminal-Bench HardGemini 3.1 Pro by 35.653.818.2+35.6
- SciCodeGemini 3.1 Pro by 20.558.738.2+20.5
- LiveCodeBench v6Gemini 3.1 Pro by 19.791.772+19.7
AgentsGemini 3.1 Pro
- GDPValGemini 3.1 Pro by 14.714.70+14.7
- τ-Bench V3 · BankingGemini 3.1 Pro by 12.721.48.7+12.7
ReasoningGemini 3.1 Pro
- Humanity's Last ExamGemini 3.1 Pro by 31.34715.7+31.3
- GPQA DiamondGemini 3.1 Pro by 18.894.175.3+18.8
- CritPtGemini 3.1 Pro by 17.717.70+17.7
FactsGemini 3.1 Pro
- AA-Omniscience · AccuracyGemini 3.1 Pro by 39.354.915.6+39.3
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 30.149.119+30.1
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 12.782.469.7+12.7
- OCRBenchv2Gemini 3.1 Pro by 1162.851.8+11
Long documentsEven
- AA-LCRGemini 3.1 Pro by 18.38263.7+18.3
- MRCR v2 8 needle 128k (average)Gemma 4 12B by 17.126.343.4+17.1
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 3.677.173.5+3.6
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.
- AA-OmniscienceGemini 3.1 Pro by 84.631.9-52.7+84.6
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 59.395.636.3+59.3
- HLE (with tools)Gemini 3.1 Pro by 46.251.45.2+46.2
- Artificial Analysis Coding IndexGemini 3.1 Pro by 37.868.831+37.8
- AA IntelligenceGemini 3.1 Pro by 15.529.714.2+15.5
- MMLU-ProGemini 3.1 Pro by 13.89177.2+13.8
- MATH-VisionGemini 3.1 Pro by 10.189.879.7+10.1
- MMMLUGemini 3.1 Pro by 9.292.683.4+9.2
- AA Agentic IndexGemini 3.1 Pro by 2.410.37.9+2.4
Questions people ask
Which is better, Gemini 3.1 Pro or Gemma 4 12B?
Gemini 3.1 Pro wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. Gemma 4 12B wins none, but costs 97% less. They are level on long documents.
Which is better for coding?
Gemini 3.1 Pro. It wins 4 of the 4 coding tests both models report; Gemma 4 12B wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Gemma 4 12B costs $0.10 and $0.30. That makes Gemma 4 12B about 97% cheaper for the same work.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 17 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.