Claude Sonnet 4 vs Muse Spark
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Muse Spark is the stronger all-rounder.
Scores updated · 24 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 software05Muse Spark5 of 5 tests
- ReasoningHard problems that need careful thinking04Muse Spark4 of 4 tests
- AgentsCarrying out multi-step tasks on its own02Muse Spark2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video02Muse Spark2 of 2 tests
- Following instructionsDoing exactly what it is asked02Muse Spark2 of 2 tests
- Long documentsFinding answers in very long texts01Muse Spark1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Muse Spark pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+36.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+30points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+26.9points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+55.1points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMuse Spark
- Terminal-Bench 2.1Muse Spark by 25.936.362.2+25.9
- Terminal-Bench HardMuse Spark by 14.431.145.5+14.4
- SciCodeMuse Spark by 11.54051.5+11.5
- SWE-bench ProMuse Spark by 9.742.752.4+9.7
- SWE-bench VerifiedMuse Spark by 4.772.777.4+4.7
AgentsMuse Spark
- GDPValMuse Spark by 15.39.624.9+15.3
- τ-Bench V3 · BankingMuse Spark by 2.916.719.6+2.9
ReasoningMuse Spark
- ARC-AGI-2Muse Spark by 36.65.942.5+36.6
- Humanity's Last ExamMuse Spark by 3010.740.7+30
- CritPtMuse Spark by 110.311.3+11
- GPQA DiamondMuse Spark by 10.777.788.4+10.7
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 55.170.915.8+55.1
- AA-Omniscience · AccuracyMuse Spark by 26.922.749.6+26.9
Images and chartsMuse Spark
- MMMU-ProMuse Spark by 18.761.880.5+18.7
- LMArena · VisionMuse Spark by 115 rating points11911306+115 rating
Following instructionsMuse Spark
- IFBenchMuse Spark by 21.254.775.9+21.2
- Multi-ChallengeMuse Spark by 18.457.175.5+18.4
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.
- τ²-Bench Telecom (AA run)Muse Spark by 26.964.691.5+26.9
- Artificial Analysis Coding IndexMuse Spark by 2137.658.6+21
- frontiermath_tier_4_v1Muse Spark by 14.6014.6+14.6
- AA IntelligenceMuse Spark by 12.418.931.3+12.4
- AA Agentic IndexMuse Spark by 11.117.628.7+11.1
- AA-OmniscienceMuse Spark by 70.27.2+7
Questions people ask
Which is better, Claude Sonnet 4 or Muse Spark?
Muse Spark 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. They are level on facts.
Which is better for coding?
Muse Spark. It wins 5 of the 5 coding tests both models report; Claude Sonnet 4 wins none.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 18 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.