Claude Opus 4 vs o1
Wins 3 of 5 areas
Coding · Reasoning · Long documents
Wins 1 of 5 areas
Following instructions
Claude Opus 4 is the stronger all-rounder.o1 is cheaper and better at following instructions.
Scores updated · 31 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 Opus 43 of 3 tests
- ReasoningHard problems that need careful thinking30Claude Opus 43 of 3 tests
- Long documentsFinding answers in very long texts10Claude Opus 41 of 1 test
- Following instructionsDoing exactly what it is asked01o11 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 each
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.
o1 costs 17% 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 Opus 4 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+31.2points ahead
- Common-sense trick questionsSimpleBench+18.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+18.2points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4
- SWE-bench VerifiedClaude Opus 4 by 31.272.541.3+31.2
- Terminal-Bench HardClaude Opus 4 by 18.231.112.9+18.2
- SciCodeClaude Opus 4 by 439.835.8+4
ReasoningClaude Opus 4
- SimpleBenchClaude Opus 4 by 18.758.840.1+18.7
- Humanity's Last ExamClaude Opus 4 by 5.312.37+5.3
- GPQA DiamondClaude Opus 4 by 4.979.674.7+4.9
Images and chartsEven
- MMMUo1 by 3.973.777.6+3.9
- LMArena · VisionClaude Opus 4 by 24 rating points11921168+24 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 3148.279.2+31
- LiveBenchClaude Opus 4 by 22.374.652.3+22.3
- metr_re_benchClaude Opus 4 by 20200+20
- SimpleQAo1 by 19.622.842.4+19.6
- τ²-Bench Telecom (AA run)Claude Opus 4 by 10.873.462.6+10.8
- TAU-bench (retail)Claude Opus 4 by 10.681.470.8+10.6
- TAU-bench (airline)Claude Opus 4 by 9.659.650+9.6
- Aider-PolyglotClaude Opus 4 by 970.761.7+9
- AIME 2025o1 by 6.275.581.7+6.2
- AIR-Bench 2024Claude Opus 4 by 5.785.780+5.7
- Artificial Analysis Coding Indexo1 by 5.73439.7+5.7
- AA IntelligenceClaude Opus 4 by 5.420.615.2+5.4
- HarmBencho1 by 4.691.796.3+4.6
- MATH-500 (EM)o1 by 294.496.4+2
- MMLUClaude Opus 4 by 1.192.991.8+1.1
- MMMLUClaude Opus 4 by 1.188.887.7+1.1
- simple_safety_testsClaude Opus 4 by 110099+1
- anthropic_red_teamtie98.998.3tie
- bbqtie97.197.3tie
- metr_swaatie99.8100tie
- XSTesttie9797tie
Questions people ask
Which is better, Claude Opus 4 or o1?
Claude Opus 4 wins three of the five areas where both have results: coding, reasoning and long documents. o1 wins following instructions, and costs 17% less. They are level on images and charts.
Which is better for coding?
Claude Opus 4. It wins 3 of the 3 coding tests both models report; o1 wins none.
Which is cheaper?
Claude Opus 4 costs $15.00 per million input tokens and $75.00 per million output tokens; o1 costs $15.00 and $60.00. That makes o1 about 17% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 10 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.