Claude Sonnet 4.6 vs Mistral Small 3.1
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Sonnet 4.6 is the stronger all-rounder.Mistral Small 3.1 is cheaper.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software30Claude Sonnet 4.63 of 3 tests
- AgentsCarrying out multi-step tasks on its own30Claude Sonnet 4.63 of 3 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.63 of 3 tests
- FactsGetting facts right instead of making them up20Claude Sonnet 4.62 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.61 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 4.61 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 Small 3.1 costs 98% 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 Claude Sonnet 4.6 pulls ahead
- Reasons across sets of long documentsAA-LCR+57.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+45.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+45points ahead
Where Mistral Small 3.1 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- Terminal-Bench HardClaude Sonnet 4.6 by 45.4537.6+45.4
- Terminal-Bench 2.1Claude Sonnet 4.6 by 4571.226.2+45
- SciCodeClaude Sonnet 4.6 by 22.350.127.8+22.3
AgentsClaude Sonnet 4.6
- GDPValClaude Sonnet 4.6 by 36.736.70+36.7
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 2734.47.4+27
- Terminal-Bench 4.0Claude Sonnet 4.6 by 330+3
ReasoningClaude Sonnet 4.6
- GPQA DiamondClaude Sonnet 4.6 by 42.187.545.4+42.1
- Humanity's Last ExamClaude Sonnet 4.6 by 29.333.64.3+29.3
- CritPtClaude Sonnet 4.6 by 3.13.10+3.1
FactsClaude Sonnet 4.6
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 29.251.622.4+29.2
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 25.840.915.1+25.8
Long documentsClaude Sonnet 4.6
- AA-LCRClaude Sonnet 4.6 by 57.78022.3+57.7
Following instructionsClaude Sonnet 4.6
- IFBenchClaude Sonnet 4.6 by 26.756.629.9+26.7
Other results5 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-OmniscienceClaude Sonnet 4.6 by 62.912.2-50.8+62.9
- τ²-Bench Telecom (AA run)Claude Sonnet 4.6 by 50.675.725.1+50.6
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 36.76326.3+36.7
- AA Agentic IndexClaude Sonnet 4.6 by 3133.12.1+31
- AA IntelligenceClaude Sonnet 4.6 by 2330.17.1+23
Questions people ask
Which is better, Claude Sonnet 4.6 or Mistral Small 3.1?
Claude Sonnet 4.6 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Mistral Small 3.1 wins none, but costs 98% less.
Which is better for coding?
Claude Sonnet 4.6. It wins 3 of the 3 coding tests both models report; Mistral Small 3.1 wins none.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Mistral Small 3.1 costs $0.11 and $0.17. That makes Mistral Small 3.1 about 98% cheaper for the same work.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.