Claude Sonnet 4.5 vs Claude Opus 5
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Claude Opus 5 is the stronger all-rounder.Claude Sonnet 4.5 is cheaper.
Scores updated · 32 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.
- CodingWriting and fixing software06Claude Opus 56 of 6 tests
- AgentsCarrying out multi-step tasks on its own06Claude Opus 56 of 6 tests
- ReasoningHard problems that need careful thinking05Claude Opus 55 of 5 tests
- Images and chartsUnderstanding pictures, charts and video02Claude Opus 52 of 2 tests
- MathCompetition and research-level math02Claude Opus 52 of 2 tests
- FactsGetting facts right instead of making them up12Claude Opus 52 of 3 tests
- Long documentsFinding answers in very long texts01Claude Opus 51 of 1 test
Long documents 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.
Claude Sonnet 4.5 costs 40% 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 5 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+76.8points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+71.2points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+70.8points ahead
Where Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.7points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5
- SWE-bench ProClaude Opus 5 by 35.643.679.2+35.6
- Terminal-Bench 2.1Claude Opus 5 by 33.355.889.1+33.3
- LMArena · WebDevClaude Opus 5 by 305 rating points13851690+305 rating
- SWE-bench MultilingualClaude Opus 5 by 22.56789.5+22.5
- SWE-bench VerifiedClaude Opus 5 by 17.878.296+17.8
- SciCodeClaude Opus 5 by 10.745.756.4+10.7
AgentsClaude Opus 5
- BrowseCompClaude Opus 5 by 71.219.690.8+71.2
- Terminal-Bench 4.0Claude Opus 5 by 49049+49
- MCP AtlasClaude Opus 5 by 4243.885.8+42
- GDPValClaude Opus 5 by 40.620.561.1+40.6
- OSWorld-VerifiedClaude Opus 5 by 2261.483.4+22
- τ-Bench V3 · BankingClaude Opus 5 by 17.624.542.1+17.6
ReasoningClaude Opus 5
- ARC-AGI-2Claude Opus 5 by 76.813.690.4+76.8
- Humanity's Last ExamClaude Opus 5 by 37.117.854.9+37.1
- CritPtClaude Opus 5 by 281.129.1+28
- SimpleBenchClaude Opus 5 by 26.354.380.6+26.3
- GPQA DiamondClaude Opus 5 by 9.883.493.2+9.8
FactsClaude Opus 5
- SimpleQA VerifiedClaude Opus 5 by 29.230.759.9+29.2
- AA-Omniscience · AccuracyClaude Opus 5 by 2832.960.9+28
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 11.750.939.2+11.7
Images and chartsClaude Opus 5
- CharXiv (RQ)Claude Opus 5 by 16.567.283.7+16.5
- MMMU-ProClaude Opus 5 by 1668.784.7+16
MathClaude Opus 5
- FrontierMath Tier 4Claude Opus 5 by 70.82.473.2+70.8
- FrontierMath Tiers 1-3 (v2)Claude Opus 5 by 61.723.985.6+61.7
Other results7 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.
- HLE (with tools)Claude Opus 5 by 39.124.563.6+39.1
- AA Agentic IndexClaude Opus 5 by 38.717.556.2+38.7
- AA-OmniscienceClaude Opus 5 by 37.2-0.137.1+37.2
- ARC-AGI-1Claude Opus 5 by 33.863.797.5+33.8
- AA IntelligenceClaude Opus 5 by 30.120.750.8+30.1
- Artificial Analysis Coding IndexClaude Opus 5 by 25.952.178+25.9
- HealthBenchClaude Opus 5 by 22.944.267.1+22.9
Questions people ask
Which is better, Claude Sonnet 4.5 or Claude Opus 5?
Claude Opus 5 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, math and long documents. Claude Sonnet 4.5 wins none, but costs 40% less.
Which is better for coding?
Claude Opus 5. It wins 6 of the 6 coding tests both models report; Claude Sonnet 4.5 wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Opus 5 costs $5.00 and $25.00. That makes Claude Sonnet 4.5 about 40% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 25 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.