Claude Opus 4 vs Claude Sonnet 4.5
Wins 0 of 6 areas
—
Wins 4 of 6 areas
Coding · Reasoning · Images and charts · Long documents
Claude Sonnet 4.5 is the stronger all-rounder.
Scores updated · 41 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software04Claude Sonnet 4.54 of 4 tests
- ReasoningHard problems that need careful thinking13Claude Sonnet 4.53 of 4 tests
- Long documentsFinding answers in very long texts02Claude Sonnet 4.52 of 2 tests
- Images and chartsUnderstanding pictures, charts and video01Claude Sonnet 4.51 of 1 test
- FactsGetting facts right instead of making them up00Even0 each · 1 tie
- Following instructionsDoing exactly what it is asked11Even1 each
Facts and images and charts 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 4.5 costs 80% 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 4.5 pulls ahead
- Recent programming contest problemsLiveCodeBench v6+16.6points ahead
- Questions about very long textsLongBench v2+6.2points ahead
- Code for real scientific research problemsSciCode+5.9points ahead
Where Claude Opus 4 pulls ahead
- Common-sense trick questionsSimpleBench+4.5points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+3.3points ahead
Every test, side by side
All 41 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- LiveCodeBench v6Claude Sonnet 4.5 by 16.647.464+16.6
- SciCodeClaude Sonnet 4.5 by 5.939.845.7+5.9
- SWE-bench VerifiedClaude Sonnet 4.5 by 4.772.577.2+4.7
- Terminal-Bench HardClaude Sonnet 4.5 by 4.531.135.6+4.5
ReasoningClaude Sonnet 4.5
- Humanity's Last ExamClaude Sonnet 4.5 by 5.512.317.8+5.5
- ARC-AGI-2Claude Sonnet 4.5 by 58.613.6+5
- SimpleBenchClaude Opus 4 by 4.558.854.3+4.5
- GPQA DiamondClaude Sonnet 4.5 by 3.879.683.4+3.8
Images and chartsClaude Sonnet 4.5
- MMMUClaude Sonnet 4.5 by 5.973.779.6+5.9
Long documentsClaude Sonnet 4.5
- LongBench v2Claude Sonnet 4.5 by 6.255.661.8+6.2
- AA-LCRClaude Sonnet 4.5 by 369.372.3+3
Following instructionsEven
- IFBenchClaude Sonnet 4.5 by 3.653.757.3+3.6
- Multi-ChallengeClaude Opus 4 by 3.358.655.3+3.3
Other results27 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.
- HMMT 2025Claude Sonnet 4.5 by 58.715.974.6+58.7
- τ²-BenchClaude Sonnet 4.5 by 415798+41
- ARC-AGI-1Claude Sonnet 4.5 by 2835.763.7+28
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 18.13452.1+18.1
- AIME 2025Claude Sonnet 4.5 by 11.575.587+11.5
- TAU-bench (airline)Claude Sonnet 4.5 by 10.459.670+10.4
- HMMT Feb. 2025Claude Sonnet 4.5 by 7.56067.5+7.5
- Terminal-BenchClaude Sonnet 4.5 by 6.843.250+6.8
- SWE-bench Verified (hard subset)Claude Sonnet 4.5 by 5.839.545.3+5.8
- TAU-bench (retail)Claude Sonnet 4.5 by 4.881.486.2+4.8
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 4.773.478.1+4.7
- vectara_answer_rateClaude Sonnet 4.5 by 4.69195.6+4.6
- τ²-Bench (Retail)Claude Sonnet 4.5 by 4.481.886.2+4.4
- AIR-Bench 2024Claude Sonnet 4.5 by 4.185.789.8+4.1
- bbqClaude Sonnet 4.5 by 1.897.198.9+1.8
- MMLU-ReduxClaude Sonnet 4.5 by 1.494.295.6+1.4
- MMLU-Protie86.687.5tie
- anthropic_red_teamtie98.998.2tie
- LiveCodeBenchtie70.471tie
- XSTesttie9796.4tie
- vectara_avg_summary_lengthtie123.2127.8tie
- HarmBenchtie91.792tie
- MMMLUtie88.889.1tie
- AA Intelligencetie20.620.7tie
- frontiermath_tier_4_v1tie4.24.2tie
- simple_safety_teststie100100tie
- vectara_factual_consistencytie8888tie
Questions people ask
Which is better, Claude Opus 4 or Claude Sonnet 4.5?
Claude Sonnet 4.5 wins four of the six areas where both have results: coding, reasoning, images and charts and long documents. Claude Opus 4 wins none. They are level on facts and following instructions.
Which is better for coding?
Claude Sonnet 4.5. It wins 4 of the 4 coding tests both models report; Claude Opus 4 wins none.
Which is cheaper?
Claude Opus 4 costs $15.00 per million input tokens and $75.00 per million output tokens; Claude Sonnet 4.5 costs $3.00 and $15.00. That makes Claude Sonnet 4.5 about 80% cheaper for the same work.
How do you compare the two?
We use the 41 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 27 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.