Claude Sonnet 4.5 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
—
Claude Sonnet 4.5 is the stronger all-rounder.Mistral Small 4 is cheaper.
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 software30Claude Sonnet 4.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 4.52 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking20Claude Sonnet 4.52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Claude Sonnet 4.52 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Sonnet 4.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 4.51 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 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 Claude Sonnet 4.5 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+34.8points ahead
- Reasons across sets of long documentsAA-LCR+22.6points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+19.6points ahead
Where Mistral Small 4 pulls ahead
No clear win on a test scored out of 100.
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.
CodingClaude Sonnet 4.5
- Terminal-Bench 2.1Claude Sonnet 4.5 by 34.855.821+34.8
- Terminal-Bench HardClaude Sonnet 4.5 by 18.235.617.4+18.2
- SciCodeClaude Sonnet 4.5 by 6.945.738.8+6.9
AgentsClaude Sonnet 4.5
- GDPValClaude Sonnet 4.5 by 20.520.50+20.5
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 19.624.54.9+19.6
- Terminal-Bench 4.0tie00tie
ReasoningClaude Sonnet 4.5
- Humanity's Last ExamClaude Sonnet 4.5 by 7.917.89.9+7.9
- GPQA DiamondClaude Sonnet 4.5 by 6.583.476.9+6.5
- CritPttie1.10.3tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 17.450.933.5+17.4
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 11.232.921.7+11.2
Images and chartsClaude Sonnet 4.5
- MMMU-ProClaude Sonnet 4.5 by 11.968.756.8+11.9
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 22.672.349.7+22.6
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 9.157.348.2+9.1
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.
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 36.978.141.2+36.9
- AA-OmniscienceClaude Sonnet 4.5 by 30.3-0.1-30.4+30.3
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 25.552.126.6+25.5
- MMLU-ProClaude Sonnet 4.5 by 9.587.578+9.5
- AA IntelligenceClaude Sonnet 4.5 by 9.420.711.3+9.4
- LiveCodeBenchClaude Sonnet 4.5 by 7.47163.6+7.4
- AIME 2025Claude Sonnet 4.5 by 3.28783.8+3.2
Questions people ask
Which is better, Claude Sonnet 4.5 or Mistral Small 4?
Claude Sonnet 4.5 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 96% less.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; Mistral Small 4 wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Mistral Small 4 costs $0.15 and $0.60. That makes Mistral Small 4 about 96% 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.