Gemini 3.1 Pro vs Gemma 4 31B
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 31B is cheaper.
Scores updated · 51 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 software80Gemini 3.1 Pro8 of 8 tests
- Images and chartsUnderstanding pictures, charts and video40Gemini 3.1 Pro4 of 4 tests
- AgentsCarrying out multi-step tasks on its own41Gemini 3.1 Pro4 of 5 tests
- ReasoningHard problems that need careful thinking30Gemini 3.1 Pro3 of 3 tests
- MathCompetition and research-level math30Gemini 3.1 Pro3 of 3 tests
- FactsGetting facts right instead of making them up31Gemini 3.1 Pro3 of 4 tests
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 of 1 test
- Long documentsFinding answers in very long texts11Even1 each
Following instructions rests on a single test.
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 31B costs 96% 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
- Short factual questions, answered correctlySimpleQA Verified+63.1points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+34.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.1points ahead
Where Gemma 4 31B pulls ahead
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+40.1points ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+7points ahead
Every test, side by side
All 51 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 30.473.843.4+30.4
- SWE-bench VerifiedGemini 3.1 Pro by 28.680.652+28.6
- SWE-bench MultilingualGemini 3.1 Pro by 25.276.951.7+25.2
- SWE-bench ProGemini 3.1 Pro by 18.554.235.7+18.5
- Terminal-Bench HardGemini 3.1 Pro by 17.453.836.4+17.4
- SciCodeGemini 3.1 Pro by 13.258.745.5+13.2
- LiveCodeBench v6Gemini 3.1 Pro by 11.791.780+11.7
- LMArena · WebDevGemini 3.1 Pro by 82 rating points14471365+82 rating
AgentsGemini 3.1 Pro
- MCP AtlasGemini 3.1 Pro by 1269.257.2+12
- GDPValGemini 3.1 Pro by 8.614.76.1+8.6
- AA IT-Bench SREGemma 4 31B by 730.337.3+7
- τ-Bench V3 · BankingGemini 3.1 Pro by 6.621.414.8+6.6
- Terminal-Bench 4.0Gemini 3.1 Pro by 440+4
ReasoningGemini 3.1 Pro
- Humanity's Last ExamGemini 3.1 Pro by 23.44723.6+23.4
- CritPtGemini 3.1 Pro by 16.317.71.4+16.3
- GPQA DiamondGemini 3.1 Pro by 8.494.185.7+8.4
FactsGemini 3.1 Pro
- SimpleQA VerifiedGemini 3.1 Pro by 63.173.510.4+63.1
- AA-Omniscience · AccuracyGemini 3.1 Pro by 34.954.920+34.9
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 34.149.115+34.1
- Vectara HHEM hallucination ratelower is betterGemma 4 31B by 310.47.4+3
Images and chartsGemini 3.1 Pro
- CharXiv (RQ)Gemini 3.1 Pro by 15.483.367.9+15.4
- MathVistaGemini 3.1 Pro by 10.990.279.3+10.9
- MMMU-ProGemini 3.1 Pro by 982.473.4+9
- LMArena · VisionGemini 3.1 Pro by 19 rating points12961277+19 rating
MathGemini 3.1 Pro
- HMMT Feb. 2026Gemini 3.1 Pro by 17.594.777.2+17.5
- AIME 2026Gemini 3.1 Pro by 9.198.389.2+9.1
- IMOAnswerBenchGemini 3.1 Pro by 6.58174.5+6.5
Long documentsEven
- MRCR v2 8 needle 128k (average)Gemma 4 31B by 40.126.366.4+40.1
- AA-LCRGemini 3.1 Pro by 12.38269.7+12.3
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 1.577.175.6+1.5
Other results21 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 79.831.9-47.9+79.8
- MCPMarkGemini 3.1 Pro by 37.855.918.1+37.8
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 35.795.659.9+35.7
- Tool-DecathlonGemini 3.1 Pro by 27.648.821.2+27.6
- Terminal-Bench 2.0Gemini 3.1 Pro by 25.668.542.9+25.6
- Artificial Analysis Coding IndexGemini 3.1 Pro by 25.468.843.4+25.4
- HLE (with tools)Gemini 3.1 Pro by 24.951.426.5+24.9
- NL2RepoGemini 3.1 Pro by 17.933.415.5+17.9
- SimpleVQAGemini 3.1 Pro by 1769.952.9+17
- AA IntelligenceGemini 3.1 Pro by 1529.714.7+15
- RealWorldQAGemini 3.1 Pro by 13.185.472.3+13.1
- t2-benchGemini 3.1 Pro by 12.999.386.4+12.9
- HMMT Nov. 2025Gemini 3.1 Pro by 7.394.887.5+7.3
- MMLU-ProGemini 3.1 Pro by 5.89185.2+5.8
- MATH-VisionGemini 3.1 Pro by 4.289.885.6+4.2
- MMMLUGemini 3.1 Pro by 4.292.688.4+4.2
- AA Agentic IndexGemini 3.1 Pro by 3.610.36.7+3.6
- vectara_avg_summary_lengthGemini 3.1 Pro by 31.9 rating points107.775.8+31.9 rating
- vectara_factual_consistencyGemma 4 31B by 389.692.6+3
- vectara_answer_ratetie99.4100tie
- τ³-Benchtie67.167.5tie
Questions people ask
Which is better, Gemini 3.1 Pro or Gemma 4 31B?
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 31B wins none, but costs 96% less. They are level on long documents.
Which is better for coding?
Gemini 3.1 Pro. It wins 8 of the 8 coding tests both models report; Gemma 4 31B 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 31B costs $0.17 and $0.40. That makes Gemma 4 31B about 96% cheaper for the same work.
How do you compare the two?
We use the 51 benchmark tests both models have published scores on. The verdict counts the 30 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.