Claude Sonnet 4 vs o3-mini
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 0 of 6 areas
—
Claude Sonnet 4 is the stronger all-rounder.o3-mini is cheaper.
Scores updated · 40 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 software31Claude Sonnet 43 of 4 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 42 of 2 tests
- FactsGetting facts right instead of making them up20Claude Sonnet 42 of 2 tests
- ReasoningHard problems that need careful thinking21Claude Sonnet 42 of 5 tests · 2 ties
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- Following instructionsDoing exactly what it is asked11Even1 each
Long documents rests on a single test.
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.
o3-mini costs 69% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+52points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+31.8points ahead
- Reasons across sets of long documentsAA-LCR+27.3points ahead
Where o3-mini pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12.4points ahead
- Code for real scientific research problemsSciCode+2.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.3points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- Terminal-Bench 2.1Claude Sonnet 4 by 31.836.34.5+31.8
- Terminal-Bench HardClaude Sonnet 4 by 2531.16.1+25
- SWE-bench VerifiedClaude Sonnet 4 by 23.472.749.3+23.4
- SciCodeo3-mini by 2.84042.8+2.8
AgentsClaude Sonnet 4
- τ-Bench V3 · BankingClaude Sonnet 4 by 11.516.75.2+11.5
- GDPValClaude Sonnet 4 by 9.79.70+9.7
ReasoningClaude Sonnet 4
- SimpleBenchClaude Sonnet 4 by 22.745.522.8+22.7
- ARC-AGI-2Claude Sonnet 4 by 2.95.93+2.9
- Humanity's Last Examo3-mini by 1.310.712+1.3
- GPQA Diamondtie77.777.3tie
- CritPttie0.30.3tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 5270.918.9+52
- AA-Omniscience · AccuracyClaude Sonnet 4 by 1.422.721.3+1.4
Following instructionsEven
- Multi-ChallengeClaude Sonnet 4 by 17.257.139.9+17.2
- IFBencho3-mini by 12.454.767.1+12.4
Other results24 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 by 42.80.2-42.6+42.8
- AIME 2024o3-mini by 36.243.479.6+36.2
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 33.364.631.3+33.3
- TAU-bench (airline)Claude Sonnet 4 by 27.66032.4+27.6
- TAU-bench (retail)Claude Sonnet 4 by 22.980.557.6+22.9
- AIME 2025Claude Sonnet 4 by 22.270.548.3+22.2
- Artificial Analysis Coding IndexClaude Sonnet 4 by 21.337.616.3+21.3
- livecodebench_hardo3-mini by 14.832.647.4+14.8
- AIR-Bench 2024Claude Sonnet 4 by 13.488.374.9+13.4
- livecodebench_mediumo3-mini by 11.57687.5+11.5
- LiveBencho3-mini by 9.874.884.6+9.8
- LiveCodeBencho3-mini by 9.268.577.7+9.2
- AA IntelligenceClaude Sonnet 4 by 7.918.911+7.9
- IFEvalo3-mini by 6.387.693.9+6.3
- ARC-AGI-1Claude Sonnet 4 by 5.54034.5+5.5
- frontiermath_tier_4_v1o3-mini by 4.204.2+4.2
- Aider-PolyglotClaude Sonnet 4 by 470.766.7+4
- HarmBenchClaude Sonnet 4 by 2.89895.2+2.8
- bbqClaude Sonnet 4 by 2.596.694.1+2.5
- XSTestClaude Sonnet 4 by 2.596.694.1+2.5
- simple_safety_testsClaude Sonnet 4 by 110099+1
- SimpleQAtie15.915tie
- anthropic_red_teamtie99.298.6tie
- livecodebench_easytie98.899.1tie
Questions people ask
Which is better, Claude Sonnet 4 or o3-mini?
Claude Sonnet 4 wins five of the six areas where both have results: coding, agents, reasoning, facts and long documents. o3-mini wins none, but costs 69% less. They are level on following instructions.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 4 coding tests both models report; o3-mini wins 1.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; o3-mini costs $1.10 and $4.40. That makes o3-mini about 69% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.