Claude Opus 4.5 vs Claude Sonnet 4
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Opus 4.5 is the stronger all-rounder.Claude Sonnet 4 is cheaper.
Scores updated · 42 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 software51Claude Opus 4.55 of 6 tests
- ReasoningHard problems that need careful thinking40Claude Opus 4.54 of 4 tests
- AgentsCarrying out multi-step tasks on its own30Claude Opus 4.53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.52 of 2 tests
- Following instructionsDoing exactly what it is asked20Claude Opus 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Opus 4.51 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
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 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 4.5 pulls ahead
- Real work tasks from 44 professionsGDPVal+37.6points ahead
- Recent programming contest problemsLiveCodeBench v6+36.3points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+31.7points ahead
Where Claude Sonnet 4 pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+49.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.9points ahead
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- SWE-bench MultilingualClaude Sonnet 4 by 49.9756.9+49.9
- LiveCodeBench v6Claude Opus 4.5 by 36.384.848.5+36.3
- Terminal-Bench HardClaude Opus 4.5 by 15.94731.1+15.9
- SciCodeClaude Opus 4.5 by 9.549.540+9.5
- SWE-bench ProClaude Opus 4.5 by 9.35242.7+9.3
- SWE-bench VerifiedClaude Opus 4.5 by 8.280.972.7+8.2
AgentsClaude Opus 4.5
- GDPValClaude Opus 4.5 by 37.647.39.7+37.6
- BrowseCompClaude Opus 4.5 by 24.83712.2+24.8
- OSWorld-VerifiedClaude Opus 4.5 by 24.166.342.2+24.1
ReasoningClaude Opus 4.5
- ARC-AGI-2Claude Opus 4.5 by 31.737.65.9+31.7
- Humanity's Last ExamClaude Opus 4.5 by 19.430.110.7+19.4
- GPQA DiamondClaude Opus 4.5 by 8.986.677.7+8.9
- CritPtClaude Opus 4.5 by 4.34.60.3+4.3
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 31.93970.9+31.9
- AA-Omniscience · AccuracyClaude Opus 4.5 by 23.946.622.7+23.9
- Vectara HHEM hallucination ratelower is bettertie10.910.3tie
Images and chartsClaude Opus 4.5
Following instructionsClaude Opus 4.5
- IFBenchClaude Opus 4.5 by 3.35854.7+3.3
- Multi-ChallengeClaude Opus 4.5 by 1.95957.1+1.9
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.
- τ²-BenchClaude Opus 4.5 by 5398.245.2+53
- AA Agentic IndexClaude Opus 4.5 by 4259.617.6+42
- ARC-AGI-1Claude Opus 4.5 by 428240+42
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 24.989.564.6+24.9
- HLE (with tools)Claude Opus 4.5 by 22.943.220.3+22.9
- AIME 2025Claude Opus 4.5 by 22.392.870.5+22.3
- LiveCodeBenchClaude Opus 4.5 by 18.58768.5+18.5
- SuperGPQAClaude Opus 4.5 by 14.970.655.7+14.9
- Multi-SWE-BenchClaude Opus 4.5 by 14.35035.7+14.3
- τ²-Bench (Retail)Claude Opus 4.5 by 13.988.975+13.9
- AA-OmniscienceClaude Opus 4.5 by 13.8140.2+13.8
- AA IntelligenceClaude Opus 4.5 by 10.229.118.9+10.2
- Artificial Analysis Coding IndexClaude Opus 4.5 by 10.247.837.6+10.2
- MMLU-ProClaude Opus 4.5 by 5.889.583.7+5.8
- MMMLUClaude Opus 4.5 by 4.390.886.5+4.3
- frontiermath_tier_4_v1Claude Opus 4.5 by 4.24.20+4.2
- vectara_avg_summary_lengthClaude Sonnet 4 by 31.3 rating points114.5145.8+31.3 rating
- MMLU-ReduxClaude Opus 4.5 by 295.693.6+2
- LiveBenchClaude Opus 4.5 by 1.27674.8+1.2
- vectara_factual_consistencytie89.189.7tie
- vectara_answer_ratetie98.798.6tie
Questions people ask
Which is better, Claude Opus 4.5 or Claude Sonnet 4?
Claude Opus 4.5 wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Claude Sonnet 4 wins none, but costs 40% less. They are level on facts.
Which is better for coding?
Claude Opus 4.5. It wins 5 of the 6 coding tests both models report; Claude Sonnet 4 wins 1.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 4 costs $3.00 and $15.00. That makes Claude Sonnet 4 about 40% cheaper for the same work.
How do you compare the two?
We use the 42 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 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.