Gemini 3.1 Pro vs Mistral Small 4
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 Small 4 is cheaper.
Scores updated · 20 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 software30Gemini 3.1 Pro3 of 3 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
- FactsGetting facts right instead of making them up20Gemini 3.1 Pro2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10Gemini 3.1 Pro1 of 1 test
- 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
Images and charts, 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 Small 4 costs 95% 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+52.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+37.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+36.4points ahead
Where Mistral Small 4 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 20 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 52.873.821+52.8
- Terminal-Bench HardGemini 3.1 Pro by 36.453.817.4+36.4
- SciCodeGemini 3.1 Pro by 19.958.738.8+19.9
AgentsGemini 3.1 Pro
- τ-Bench V3 · BankingGemini 3.1 Pro by 16.521.44.9+16.5
- GDPValGemini 3.1 Pro by 14.714.70+14.7
- Terminal-Bench 4.0Gemini 3.1 Pro by 440+4
ReasoningGemini 3.1 Pro
- Humanity's Last ExamGemini 3.1 Pro by 37.1479.9+37.1
- CritPtGemini 3.1 Pro by 17.417.70.3+17.4
- GPQA DiamondGemini 3.1 Pro by 17.294.176.9+17.2
FactsGemini 3.1 Pro
- AA-Omniscience · AccuracyGemini 3.1 Pro by 33.254.921.7+33.2
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 15.649.133.5+15.6
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 25.682.456.8+25.6
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 28.977.148.2+28.9
Other results6 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 62.331.9-30.4+62.3
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 54.495.641.2+54.4
- Artificial Analysis Coding IndexGemini 3.1 Pro by 42.268.826.6+42.2
- LiveCodeBenchGemini 3.1 Pro by 28.191.763.6+28.1
- AA IntelligenceGemini 3.1 Pro by 18.429.711.3+18.4
- MMLU-ProGemini 3.1 Pro by 139178+13
Questions people ask
Which is better, Gemini 3.1 Pro or Mistral Small 4?
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 Small 4 wins none, but costs 95% less.
Which is better for coding?
Gemini 3.1 Pro. It wins 3 of the 3 coding tests both models report; Mistral Small 4 wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Mistral Small 4 costs $0.15 and $0.60. That makes Mistral Small 4 about 95% cheaper for the same work.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.