Claude Sonnet 4.5 vs Command A+
Wins 5 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents
Wins 1 of 7 areas
Following instructions
Claude Sonnet 4.5 is the stronger all-rounder.Command A+ is cheaper and better at following instructions.
Scores updated · 22 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.
- Images and chartsUnderstanding pictures, charts and video30Claude Sonnet 4.53 of 4 tests · 1 tie
- CodingWriting and fixing software30Claude Sonnet 4.53 of 3 tests
- ReasoningHard problems that need careful thinking20Claude Sonnet 4.52 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10Claude Sonnet 4.51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- Following instructionsDoing exactly what it is asked01Command A+1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Command A+ costs 90% 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
- Command-line tasks in a real terminalTerminal-Bench 2.1+33points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+24points ahead
- Reasons across sets of long documentsAA-LCR+19.6points ahead
Where Command A+ pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+16.6points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench 2.1Claude Sonnet 4.5 by 3355.822.8+33
- Terminal-Bench HardClaude Sonnet 4.5 by 10.635.625+10.6
- SciCodeClaude Sonnet 4.5 by 7.245.738.5+7.2
AgentsClaude Sonnet 4.5
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 18.524.56+18.5
- Terminal-Bench 4.0tie00.5tie
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 7.383.476.1+7.3
- Humanity's Last ExamClaude Sonnet 4.5 by 5.817.812+5.8
- CritPttie1.10.3tie
FactsEven
- AA-Omniscience · Non-hallucinationCommand A+ by 34.950.985.8+34.9
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 2432.98.9+24
Images and chartsClaude Sonnet 4.5
- CharXiv (RQ)Claude Sonnet 4.5 by 14.567.252.7+14.5
- MMMU-ProClaude Sonnet 4.5 by 5.568.763.2+5.5
- MMMUClaude Sonnet 4.5 by 4.579.675.1+4.5
- MathVistatie79.880.6tie
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 19.672.352.7+19.6
Following instructionsCommand A+
- IFBenchCommand A+ by 16.657.373.9+16.6
Other results6 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 4.5 by 24.352.127.8+24.3
- AA Agentic IndexClaude Sonnet 4.5 by 13.917.53.6+13.9
- AA IntelligenceClaude Sonnet 4.5 by 7.620.713.1+7.6
- AA-OmniscienceClaude Sonnet 4.5 by 3.9-0.1-4+3.9
- AIME 2025Command A+ by 38790+3
- τ²-Bench Telecom (AA run)Command A+ by 2.678.180.7+2.6
Questions people ask
Which is better, Claude Sonnet 4.5 or Command A+?
Claude Sonnet 4.5 wins five of the seven areas where both have results: coding, agents, reasoning, images and charts and long documents. Command A+ wins following instructions, and costs 90% less. They are level on facts.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; Command A+ wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Command A+ costs $0.30 and $1.50. That makes Command A+ about 90% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.