Claude Sonnet 4.6 vs Muse Spark 1.1
Wins 1 of 8 areas
Long documents
Wins 6 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Following instructions
Muse Spark 1.1 is the stronger all-rounder.Claude Sonnet 4.6 is better at long documents.
Scores updated · 34 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 software15Muse Spark 1.15 of 6 tests
- ReasoningHard problems that need careful thinking04Muse Spark 1.14 of 4 tests
- Images and chartsUnderstanding pictures, charts and video02Muse Spark 1.12 of 2 tests
- AgentsCarrying out multi-step tasks on its own23Muse Spark 1.13 of 5 tests
- FactsGetting facts right instead of making them up12Muse Spark 1.12 of 3 tests
- Following instructionsDoing exactly what it is asked01Muse Spark 1.11 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 4.61 of 1 test
- MathCompetition and research-level math00Even0 each · 1 tie
Math, 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.
Muse Spark 1.1 costs 69% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Muse Spark 1.1 pulls ahead
- Multi-step tasks using many real software toolsMCP Atlas+26.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+25points ahead
- Reasoning about charts from research papersCharXiv (RQ)+16.8points ahead
Where Claude Sonnet 4.6 pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+2.6points ahead
- Reasons across sets of long documentsAA-LCR+2.3points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+2.1points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMuse Spark 1.1
- LiveBench · Agentic CodingMuse Spark 1.1 by 15.942.658.5+15.9
- SciCodeMuse Spark 1.1 by 8.750.158.8+8.7
- Terminal-Bench 2.1Muse Spark 1.1 by 6.771.277.9+6.7
- SWE-bench ProMuse Spark 1.1 by 3.458.161.5+3.4
- LiveBench · CodingClaude Sonnet 4.6 by 2.179.377.2+2.1
- LMArena · WebDevMuse Spark 1.1 by 20 rating points15221542+20 rating
AgentsMuse Spark 1.1
- MCP AtlasMuse Spark 1.1 by 26.861.388.1+26.8
- OSWorld-VerifiedMuse Spark 1.1 by 8.372.580.8+8.3
- Terminal-Bench 4.0Muse Spark 1.1 by 3.136.1+3.1
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 2.634.431.8+2.6
- GDPValClaude Sonnet 4.6 by 136.735.7+1
ReasoningMuse Spark 1.1
- Humanity's Last ExamMuse Spark 1.1 by 12.633.646.2+12.6
- CritPtMuse Spark 1.1 by 123.115.1+12
- LiveBench · ReasoningMuse Spark 1.1 by 2.984.887.7+2.9
- GPQA DiamondMuse Spark 1.1 by 2.387.589.8+2.3
FactsMuse Spark 1.1
- SimpleQA VerifiedMuse Spark 1.1 by 2532.857.8+25
- AA-Omniscience · AccuracyMuse Spark 1.1 by 11.240.952+11.2
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 1.651.650+1.6
Images and chartsMuse Spark 1.1
- CharXiv (RQ)Muse Spark 1.1 by 16.871.688.4+16.8
- LMArena · VisionMuse Spark 1.1 by 11 rating points12831294+11 rating
Following instructionsMuse Spark 1.1
- LiveBench · Instruction FollowingMuse Spark 1.1 by 6.463.269.6+6.4
Other results11 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.
- ToolathlonMuse Spark 1.1 by 34.64175.6+34.6
- DeepSWE 1.1Muse Spark 1.1 by 233053+23
- AA-OmniscienceMuse Spark 1.1 by 15.912.228.1+15.9
- HealthBench ProfessionalMuse Spark 1.1 by 15.144.259.3+15.1
- Artificial Analysis Coding IndexMuse Spark 1.1 by 8.36371.3+8.3
- Finance Agent v2Muse Spark 1.1 by 6.25157.2+6.2
- AA Agentic IndexClaude Sonnet 4.6 by 5.633.127.5+5.6
- livebench_data_analysisClaude Sonnet 4.6 by 5.47872.5+5.4
- AA IntelligenceMuse Spark 1.1 by 3.630.133.7+3.6
- CharXiv Reasoning (With tools)Muse Spark 1.1 by 3.185.388.4+3.1
- livebench_languageClaude Sonnet 4.6 by 1.876.174.3+1.8
Questions people ask
Which is better, Claude Sonnet 4.6 or Muse Spark 1.1?
Muse Spark 1.1 wins six of the eight areas we test: coding, agents, reasoning, facts, images and charts and following instructions. Claude Sonnet 4.6 wins long documents. They are level on math.
Which is better for coding?
Muse Spark 1.1. It wins 5 of the 6 coding tests both models report; Claude Sonnet 4.6 wins 1.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Muse Spark 1.1 costs $1.25 and $4.25. That makes Muse Spark 1.1 about 69% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.