Claude Opus 4.5 vs o3
Wins 5 of 8 areas
Coding · Reasoning · Facts · Math · Long documents
Wins 2 of 8 areas
Images and charts · Following instructions
Claude Opus 4.5 is the stronger all-rounder.o3 is cheaper and better at images and charts.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 thinking40Claude Opus 4.54 of 4 tests
- CodingWriting and fixing software30Claude Opus 4.53 of 3 tests
- Long documentsFinding answers in very long texts20Claude Opus 4.52 of 2 tests
- FactsGetting facts right instead of making them up21Claude Opus 4.52 of 3 tests
- MathCompetition and research-level math10Claude Opus 4.51 of 1 test
- Images and chartsUnderstanding pictures, charts and video13o33 of 4 tests
- Following instructionsDoing exactly what it is asked02o32 of 2 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each
Math 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 costs 67% 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 Opus 4.5 pulls ahead
- Real work tasks from 44 professionsGDPVal+34.5points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+31.1points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+27.1points ahead
Where o3 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+13.4points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+12.7points ahead
- Reasoning about charts from research papersCharXiv (RQ)+11.4points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- SWE-bench VerifiedClaude Opus 4.5 by 11.880.969.1+11.8
- Terminal-Bench HardClaude Opus 4.5 by 9.94737.1+9.9
- SciCodeClaude Opus 4.5 by 8.549.541+8.5
AgentsEven
- GDPValClaude Opus 4.5 by 34.547.312.8+34.5
- BrowseCompo3 by 12.73749.7+12.7
ReasoningClaude Opus 4.5
- ARC-AGI-2Claude Opus 4.5 by 31.137.66.5+31.1
- Humanity's Last ExamClaude Opus 4.5 by 1030.120.1+10
- GPQA DiamondClaude Opus 4.5 by 3.986.682.7+3.9
- CritPtClaude Opus 4.5 by 3.54.61.1+3.5
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 27.13911.9+27.1
- AA-Omniscience · AccuracyClaude Opus 4.5 by 846.638.6+8
- SimpleQA Verifiedo3 by 3.745.749.4+3.7
Images and chartso3
- CharXiv (RQ)o3 by 11.467.278.6+11.4
- MathVistao3 by 6.680.286.8+6.6
- MMMU-ProClaude Opus 4.5 by 3.97470.1+3.9
- MMMUo3 by 2.280.782.9+2.2
Long documentsClaude Opus 4.5
- LongBench v2Claude Opus 4.5 by 5.664.458.8+5.6
- AA-LCRClaude Opus 4.5 by 2.677.374.7+2.6
Following instructionso3
- IFBencho3 by 13.45871.4+13.4
- Multi-Challengeo3 by 1.45960.4+1.4
Other results15 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 Opus 4.5 by 29.514-15.6+29.5
- metr_re_benchClaude Opus 4.5 by 254015+25
- AA Agentic IndexClaude Opus 4.5 by 23.559.636.1+23.5
- ARC-AGI-1Claude Opus 4.5 by 21.28260.8+21.2
- HMMT Feb. 2025Claude Opus 4.5 by 15.492.977.5+15.4
- Artificial Analysis Coding IndexClaude Opus 4.5 by 9.447.838.4+9.4
- AA IntelligenceClaude Opus 4.5 by 8.929.120.2+8.9
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 8.889.580.7+8.8
- metr_hcastClaude Opus 4.5 by 8.773.464.7+8.7
- τ²-Bench (Retail)Claude Opus 4.5 by 8.788.980.2+8.7
- AIME 2025Claude Opus 4.5 by 6.492.886.4+6.4
- MMLU-ProClaude Opus 4.5 by 4.589.585+4.5
- LiveCodeBenchClaude Opus 4.5 by 2.38784.7+2.3
- frontiermath_tier_4_v1Claude Opus 4.5 by 2.14.22.1+2.1
- VideoMMMUClaude Opus 4.5 by 1.184.483.3+1.1
Questions people ask
Which is better, Claude Opus 4.5 or o3?
Claude Opus 4.5 wins five of the eight areas we test: coding, reasoning, facts, math and long documents. o3 wins images and charts and following instructions, and costs 67% less. They are level on agents.
Which is better for coding?
Claude Opus 4.5. It wins 3 of the 3 coding tests both models report; o3 wins none.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; o3 costs $2.00 and $8.00. That makes o3 about 67% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.