Claude 3.7 Sonnet vs o1
Wins 3 of 7 areas
Coding · Agents · Reasoning
Wins 3 of 7 areas
Images and charts · Long documents · Following instructions
The two are evenly matched.Claude 3.7 Sonnet is better at reasoning and coding; o1 at images and charts and long documents.
Scores updated · 34 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 3.7 Sonnet3 of 4 tests · 1 tie
- CodingWriting and fixing software30Claude 3.7 Sonnet3 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Claude 3.7 Sonnet1 of 1 test
- Images and chartsUnderstanding pictures, charts and video01o11 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01o11 of 1 test
- Following instructionsDoing exactly what it is asked01o11 of 1 test
- FactsGetting facts right instead of making them up11Even1 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 3.7 Sonnet 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 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+29.6points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+29points ahead
- Real work tasks from 44 professionsGDPVal+15.9points ahead
Where o1 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+22points ahead
- Reasons across sets of long documentsAA-LCR+13.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.5points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.7 Sonnet
- SWE-bench VerifiedClaude 3.7 Sonnet by 2970.341.3+29
- Terminal-Bench HardClaude 3.7 Sonnet by 8.321.212.9+8.3
- SciCodeClaude 3.7 Sonnet by 4.540.335.8+4.5
ReasoningClaude 3.7 Sonnet
- SimpleBenchClaude 3.7 Sonnet by 6.346.440.1+6.3
- Humanity's Last ExamClaude 3.7 Sonnet by 2.79.77+2.7
- GPQA DiamondClaude 3.7 Sonnet by 2.577.274.7+2.5
- CritPttie0.90.3tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 29.66030.4+29.6
- AA-Omniscience · Accuracyo1 by 6.52834.5+6.5
Images and chartso1
- MMMUo1 by 2.67577.6+2.6
- LMArena · Visiontie11691168tie
Other results20 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 2025o1 by 26.954.881.7+26.9
- HarmBencho1 by 1284.396.3+12
- metr_hcastClaude 3.7 Sonnet by 11.654.242.6+11.6
- TAU-bench (retail)Claude 3.7 Sonnet by 10.481.270.8+10.4
- AA-OmniscienceClaude 3.7 Sonnet by 10.3-0.7-11.1+10.3
- TAU-bench (airline)Claude 3.7 Sonnet by 8.458.450+8.4
- τ²-Bench Telecom (AA run)o1 by 7.954.762.6+7.9
- AA Agentic IndexClaude 3.7 Sonnet by 5.93731.1+5.9
- bbqo1 by 5.292.197.3+5.2
- Artificial Analysis Coding Indexo1 by 3.336.439.7+3.3
- AA IntelligenceClaude 3.7 Sonnet by 2.517.715.2+2.5
- AIR-Bench 2024Claude 3.7 Sonnet by 1.881.880+1.8
- MMMLUo1 by 1.686.187.7+1.6
- anthropic_red_teamClaude 3.7 Sonnet by 1.499.798.3+1.4
- Aider-Polygloto1 by 1.360.461.7+1.3
- metr_swaao1 by 1.398.7100+1.3
- simple_safety_testsClaude 3.7 Sonnet by 110099+1
- XSTesttie96.497tie
- MATH-500 (EM)tie96.296.4tie
- metr_re_benchtie00tie
Questions people ask
Which is better, Claude 3.7 Sonnet or o1?
Claude 3.7 Sonnet and o1 each win three of the seven areas where both have results. Claude 3.7 Sonnet wins coding, agents and reasoning; o1 wins images and charts, long documents and following instructions. Claude 3.7 Sonnet costs 76% less. They are level on facts.
Which is better for coding?
Claude 3.7 Sonnet. It wins 3 of the 3 coding tests both models report; o1 wins none.
Which is cheaper?
Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; o1 costs $15.00 and $60.00. That makes Claude 3.7 Sonnet about 76% cheaper for the same work.
How do you compare the two?
We use the 34 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 20 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.