Claude Opus 4.5 vs Claude Sonnet 5
Wins 1 of 8 areas
Facts
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Claude Sonnet 5 is the stronger all-rounder.Claude Opus 4.5 is better at facts.
Scores updated · 33 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.
- CodingWriting and fixing software07Claude Sonnet 57 of 7 tests
- ReasoningHard problems that need careful thinking04Claude Sonnet 54 of 4 tests
- AgentsCarrying out multi-step tasks on its own03Claude Sonnet 53 of 3 tests
- MathCompetition and research-level math03Claude Sonnet 53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Claude Sonnet 52 of 2 tests
- Long documentsFinding answers in very long texts01Claude Sonnet 51 of 1 test
- Following instructionsDoing exactly what it is asked01Claude Sonnet 51 of 1 test
- FactsGetting facts right instead of making them up21Claude Opus 4.52 of 3 tests
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 5 costs 60% 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 Sonnet 5 pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+71.3points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+47.7points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+31.2points ahead
Where Claude Opus 4.5 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+12points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.5points ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5
- SWE-bench MultilingualClaude Sonnet 5 by 71.3778.3+71.3
- LiveBench · Agentic CodingClaude Sonnet 5 by 19.739.759.4+19.7
- SWE-bench ProClaude Sonnet 5 by 11.25263.2+11.2
- LMArena · WebDevClaude Sonnet 5 by 72 rating points14691541+72 rating
- SciCodeClaude Sonnet 5 by 4.849.554.3+4.8
- SWE-bench VerifiedClaude Sonnet 5 by 4.380.985.2+4.3
- LiveBench · CodingClaude Sonnet 5 by 179.780.7+1
AgentsClaude Sonnet 5
- BrowseCompClaude Sonnet 5 by 47.73784.7+47.7
- OSWorld-VerifiedClaude Sonnet 5 by 14.966.381.2+14.9
- GDPValClaude Sonnet 5 by 147.348.3+1
ReasoningClaude Sonnet 5
- CritPtClaude Sonnet 5 by 12.34.616.9+12.3
- Humanity's Last ExamClaude Sonnet 5 by 11.230.141.3+11.2
- LiveBench · ReasoningClaude Sonnet 5 by 8.680.188.7+8.6
- GPQA DiamondClaude Sonnet 5 by 4.586.691.1+4.5
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 5 by 21.63960.6+21.6
- SimpleQA VerifiedClaude Opus 4.5 by 1245.733.7+12
- AA-Omniscience · AccuracyClaude Opus 4.5 by 6.546.640+6.5
Images and chartsClaude Sonnet 5
- CharXiv (RQ)Claude Sonnet 5 by 21.167.288.3+21.1
- MMMU-ProClaude Sonnet 5 by 3.37477.3+3.3
MathClaude Sonnet 5
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5 by 31.234.465.6+31.2
- FrontierMath Tier 4Claude Sonnet 5 by 24.44.929.3+24.4
- LiveBench · MathematicsClaude Sonnet 5 by 2.590.492.9+2.5
Following instructionsClaude Sonnet 5
- LiveBench · Instruction FollowingClaude Sonnet 5 by 1.362.563.9+1.3
Other results9 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.
- Artificial Analysis Coding IndexClaude Sonnet 5 by 23.747.871.5+23.7
- Terminal-Bench 2.0Claude Sonnet 5 by 21.159.380.4+21.1
- AA Agentic IndexClaude Opus 4.5 by 15.359.644.3+15.3
- HLE (with tools)Claude Sonnet 5 by 14.243.257.4+14.2
- ToolathlonClaude Sonnet 5 by 10.843.554.3+10.8
- AA IntelligenceClaude Sonnet 5 by 9.129.138.2+9.1
- livebench_languageClaude Opus 4.5 by 6.381.375+6.3
- livebench_data_analysisClaude Opus 4.5 by 2.774.471.7+2.7
- AA-OmniscienceClaude Sonnet 5 by 2.51416.4+2.5
Questions people ask
Which is better, Claude Opus 4.5 or Claude Sonnet 5?
Claude Sonnet 5 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Claude Opus 4.5 wins facts.
Which is better for coding?
Claude Sonnet 5. It wins 7 of the 7 coding tests both models report; Claude Opus 4.5 wins none.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 5 costs $2.00 and $10.00. That makes Claude Sonnet 5 about 60% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.