Gemini 3.1 Pro vs Mistral Large 3
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Gemini 3.1 Pro is the stronger all-rounder.Mistral Large 3 is cheaper.
Scores updated · 28 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 software40Gemini 3.1 Pro4 of 4 tests
- ReasoningHard problems that need careful thinking40Gemini 3.1 Pro4 of 4 tests
- AgentsCarrying out multi-step tasks on its own30Gemini 3.1 Pro3 of 3 tests
- FactsGetting facts right instead of making them up30Gemini 3.1 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3.1 Pro2 of 2 tests
- Long documentsFinding answers in very long texts10Gemini 3.1 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 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.
Mistral Large 3 costs 86% 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+61.8points ahead
- Common-sense trick questionsSimpleBench+59.2points ahead
- Reasons across sets of long documentsAA-LCR+46points ahead
Where Mistral Large 3 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 28 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 61.873.812+61.8
- Terminal-Bench HardGemini 3.1 Pro by 37.953.815.9+37.9
- SciCodeGemini 3.1 Pro by 22.158.736.6+22.1
- LMArena · WebDevGemini 3.1 Pro by 217 rating points14471230+217 rating
AgentsGemini 3.1 Pro
- τ-Bench V3 · BankingGemini 3.1 Pro by 15.621.45.8+15.6
- GDPValGemini 3.1 Pro by 14.714.70+14.7
- Terminal-Bench 4.0Gemini 3.1 Pro by 440+4
ReasoningGemini 3.1 Pro
- SimpleBenchGemini 3.1 Pro by 59.279.620.4+59.2
- Humanity's Last ExamGemini 3.1 Pro by 42.8474.2+42.8
- GPQA DiamondGemini 3.1 Pro by 26.194.168+26.1
- CritPtGemini 3.1 Pro by 17.717.70+17.7
FactsGemini 3.1 Pro
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 35.149.114+35.1
- AA-Omniscience · AccuracyGemini 3.1 Pro by 29.954.924.9+29.9
- Vectara HHEM hallucination ratelower is betterGemini 3.1 Pro by 4.110.414.5+4.1
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 26.782.455.7+26.7
- LMArena · VisionGemini 3.1 Pro by 74 rating points12961222+74 rating
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 40.977.136.2+40.9
Other results10 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 71.531.9-39.6+71.5
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 7195.624.6+71
- LiveCodeBenchGemini 3.1 Pro by 57.391.734.4+57.3
- Artificial Analysis Coding IndexGemini 3.1 Pro by 48.768.820.1+48.7
- AA IntelligenceGemini 3.1 Pro by 20.429.79.3+20.4
- MMMLUGemini 3.1 Pro by 18.492.674.2+18.4
- AA Agentic IndexGemini 3.1 Pro by 7.910.32.4+7.9
- vectara_factual_consistencyGemini 3.1 Pro by 4.189.685.5+4.1
- vectara_answer_ratetie99.498.8tie
- vectara_avg_summary_lengthtie107.7112.7tie
Questions people ask
Which is better, Gemini 3.1 Pro or Mistral Large 3?
Gemini 3.1 Pro wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Mistral Large 3 wins none, but costs 86% less.
Which is better for coding?
Gemini 3.1 Pro. It wins 4 of the 4 coding tests both models report; Mistral Large 3 wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Mistral Large 3 costs $0.50 and $1.50. That makes Mistral Large 3 about 86% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.