Claude Sonnet 4 vs o1
Wins 3 of 7 areas
Coding · Reasoning · Long documents
Wins 2 of 7 areas
Agents · Following instructions
Claude Sonnet 4 wins more areas, narrowly.o1 is better at agents.
Scores updated · 35 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.
- ReasoningHard problems that need careful thinking30Claude Sonnet 43 of 4 tests · 1 tie
- CodingWriting and fixing software30Claude Sonnet 43 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- AgentsCarrying out multi-step tasks on its own01o11 of 1 test
- Following instructionsDoing exactly what it is asked01o11 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
- Images and chartsUnderstanding pictures, charts and video11Even1 each
Agents, 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.
Claude Sonnet 4 costs 76% 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+40.5points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+31.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+18.2points ahead
Where o1 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.6points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.8points ahead
- College exam questions with charts, maps and diagramsMMMU+3.2points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- SWE-bench VerifiedClaude Sonnet 4 by 31.472.741.3+31.4
- Terminal-Bench HardClaude Sonnet 4 by 18.231.112.9+18.2
- SciCodeClaude Sonnet 4 by 4.24035.8+4.2
ReasoningClaude Sonnet 4
- SimpleBenchClaude Sonnet 4 by 5.445.540.1+5.4
- Humanity's Last ExamClaude Sonnet 4 by 3.710.77+3.7
- GPQA DiamondClaude Sonnet 4 by 377.774.7+3
- CritPttie0.30.3tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 40.570.930.4+40.5
- AA-Omniscience · Accuracyo1 by 11.822.734.5+11.8
Images and chartsEven
- MMMUo1 by 3.274.477.6+3.2
- LMArena · VisionClaude Sonnet 4 by 23 rating points11911168+23 rating
Other results21 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 2024o1 by 35.843.479.2+35.8
- SimpleQAo1 by 26.515.942.4+26.5
- LiveBenchClaude Sonnet 4 by 22.574.852.3+22.5
- AA Agentic Indexo1 by 13.517.631.1+13.5
- AA-OmniscienceClaude Sonnet 4 by 11.20.2-11.1+11.2
- AIME 2025o1 by 11.270.581.7+11.2
- TAU-bench (airline)Claude Sonnet 4 by 106050+10
- TAU-bench (retail)Claude Sonnet 4 by 9.780.570.8+9.7
- Aider-PolyglotClaude Sonnet 4 by 970.761.7+9
- AIR-Bench 2024Claude Sonnet 4 by 8.388.380+8.3
- AA IntelligenceClaude Sonnet 4 by 3.718.915.2+3.7
- MATH-500 (EM)o1 by 2.49496.4+2.4
- Artificial Analysis Coding Indexo1 by 2.137.639.7+2.1
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 264.662.6+2
- HarmBenchClaude Sonnet 4 by 1.79896.3+1.7
- MMMLUo1 by 1.286.587.7+1.2
- simple_safety_testsClaude Sonnet 4 by 110099+1
- anthropic_red_teamtie99.298.3tie
- bbqtie96.697.3tie
- XSTesttie96.697tie
- MMLUtie91.591.8tie
Questions people ask
Which is better, Claude Sonnet 4 or o1?
Claude Sonnet 4 wins three of the seven areas where both have results: coding, reasoning and long documents. o1 wins agents and following instructions. They are level on facts and images and charts.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 3 coding tests both models report; o1 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; o1 costs $15.00 and $60.00. That makes Claude Sonnet 4 about 76% cheaper for the same work.
How do you compare the two?
We use the 35 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 21 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.