Claude Opus 4.7 vs Claude Sonnet 4
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 1 of 7 areas
Facts
Claude Opus 4.7 is the stronger all-rounder.Claude Sonnet 4 is cheaper and better at facts.
Scores updated · 35 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 software60Claude Opus 4.76 of 6 tests
- ReasoningHard problems that need careful thinking50Claude Opus 4.75 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Opus 4.74 of 4 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.72 of 2 tests
- Long documentsFinding answers in very long texts10Claude Opus 4.71 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Opus 4.71 of 1 test
- FactsGetting facts right instead of making them up12Claude Sonnet 42 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 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 4.7 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+69.9points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+67.1points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+46.8points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+13.2points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.7
- Terminal-Bench 2.1Claude Opus 4.7 by 46.883.136.3+46.8
- SWE-bench MultilingualClaude Opus 4.7 by 23.680.556.9+23.6
- SWE-bench ProClaude Opus 4.7 by 21.664.342.7+21.6
- Terminal-Bench HardClaude Opus 4.7 by 20.451.531.1+20.4
- SWE-bench VerifiedClaude Opus 4.7 by 14.987.672.7+14.9
- SciCodeClaude Opus 4.7 by 14.554.540+14.5
AgentsClaude Opus 4.7
- BrowseCompClaude Opus 4.7 by 67.179.312.2+67.1
- OSWorld-VerifiedClaude Opus 4.7 by 35.87842.2+35.8
- GDPValClaude Opus 4.7 by 33.142.89.7+33.1
- τ-Bench V3 · BankingClaude Opus 4.7 by 17.934.616.7+17.9
ReasoningClaude Opus 4.7
- ARC-AGI-2Claude Opus 4.7 by 69.975.85.9+69.9
- Humanity's Last ExamClaude Opus 4.7 by 31.642.310.7+31.6
- SimpleBenchClaude Opus 4.7 by 16.261.745.5+16.2
- GPQA DiamondClaude Opus 4.7 by 13.791.477.7+13.7
- CritPtClaude Opus 4.7 by 11.7120.3+11.7
FactsClaude Sonnet 4
- AA-Omniscience · AccuracyClaude Opus 4.7 by 26.248.922.7+26.2
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 13.257.770.9+13.2
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4 by 1.71210.3+1.7
Images and chartsClaude Opus 4.7
- MMMU-ProClaude Opus 4.7 by 1778.861.8+17
- LMArena · VisionClaude Opus 4.7 by 122 rating points13131191+122 rating
Following instructionsClaude Opus 4.7
- IFBenchClaude Opus 4.7 by 3.958.654.7+3.9
Other results13 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.
- ARC-AGI-1Claude Opus 4.7 by 529240+52
- Artificial Analysis Coding IndexClaude Opus 4.7 by 3673.637.6+36
- HLE (with tools)Claude Opus 4.7 by 34.454.720.3+34.4
- AA-OmniscienceClaude Opus 4.7 by 27.127.30.2+27.1
- τ²-Bench Telecom (AA run)Claude Opus 4.7 by 2488.664.6+24
- frontiermath_tier_4_v1Claude Opus 4.7 by 22.922.90+22.9
- AA Agentic IndexClaude Opus 4.7 by 21.939.517.6+21.9
- AA IntelligenceClaude Opus 4.7 by 21.840.718.9+21.8
- MMMLUClaude Opus 4.7 by 591.586.5+5
- LiveBenchClaude Opus 4.7 by 2.176.974.8+2.1
- vectara_factual_consistencyClaude Sonnet 4 by 1.78889.7+1.7
- vectara_answer_ratetie9898.6tie
- vectara_avg_summary_lengthtie149.1145.8tie
Questions people ask
Which is better, Claude Opus 4.7 or Claude Sonnet 4?
Claude Opus 4.7 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 facts, and costs 40% less.
Which is better for coding?
Claude Opus 4.7. It wins 6 of the 6 coding tests both models report; Claude Sonnet 4 wins none.
Which is cheaper?
Claude Opus 4.7 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 35 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.