Llama 4 Maverick vs Mistral Small 4
Wins 1 of 7 areas
Images and charts
Wins 4 of 7 areas
Coding · Agents · Reasoning · Following instructions
Mistral Small 4 wins more areas, narrowly.Llama 4 Maverick is better at images and charts.
Scores updated · 21 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 software03Mistral Small 43 of 3 tests
- ReasoningHard problems that need careful thinking02Mistral Small 42 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01Mistral Small 41 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01Mistral Small 41 of 1 test
- Images and chartsUnderstanding pictures, charts and video10Llama 4 Maverick1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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 33% 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 Mistral Small 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+13.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+10.6points ahead
Where Llama 4 Maverick pulls ahead
- Harder college exam questions with imagesMMMU-Pro+5.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.2points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMistral Small 4
- Terminal-Bench 2.1Mistral Small 4 by 13.17.921+13.1
- Terminal-Bench HardMistral Small 4 by 10.66.817.4+10.6
- SciCodeMistral Small 4 by 7.131.738.8+7.1
AgentsMistral Small 4
- τ-Bench V3 · BankingMistral Small 4 by 1.23.74.9+1.2
- GDPValtie00tie
- Terminal-Bench 4.0tie00tie
ReasoningMistral Small 4
- GPQA DiamondMistral Small 4 by 9.867.176.9+9.8
- Humanity's Last ExamMistral Small 4 by 54.99.9+5
- CritPttie00.3tie
FactsEven
- AA-Omniscience · Non-hallucinationMistral Small 4 by 22.411.133.5+22.4
- AA-Omniscience · AccuracyLlama 4 Maverick by 3.224.921.7+3.2
Images and chartsLlama 4 Maverick
- MMMU-ProLlama 4 Maverick by 5.362.156.8+5.3
Following instructionsMistral Small 4
- IFBenchMistral Small 4 by 5.24348.2+5.2
Other results7 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.
- AIME 2025Mistral Small 4 by 61.322.583.8+61.3
- τ²-Bench Telecom (AA run)Mistral Small 4 by 23.417.841.2+23.4
- LiveCodeBenchMistral Small 4 by 20.243.463.6+20.2
- AA-OmniscienceMistral Small 4 by 11.4-41.9-30.4+11.4
- Artificial Analysis Coding IndexMistral Small 4 by 10.316.326.6+10.3
- MMLU-ProLlama 4 Maverick by 2.580.578+2.5
- AA IntelligenceMistral Small 4 by 1.31011.3+1.3
Questions people ask
Which is better, Llama 4 Maverick or Mistral Small 4?
Mistral Small 4 wins four of the seven areas where both have results: coding, agents, reasoning and following instructions. Llama 4 Maverick wins images and charts. They are level on facts and long documents.
Which is better for coding?
Mistral Small 4. It wins 3 of the 3 coding tests both models report; Llama 4 Maverick wins none.
Which is cheaper?
Llama 4 Maverick costs $0.25 per million input tokens and $0.87 per million output tokens; Mistral Small 4 costs $0.15 and $0.60. That makes Mistral Small 4 about 33% cheaper for the same work.
How do you compare the two?
We use the 21 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 7 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.