Claude Sonnet 5 vs Muse Spark 1.2
Wins 4 of 8 areas
Coding · Agents · Math · Long documents
Wins 4 of 8 areas
Reasoning · Facts · Images and charts · Following instructions
The two are evenly matched.Claude Sonnet 5 is better at agents and coding; Muse Spark 1.2 at reasoning and facts.
Scores updated · 30 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.
- ReasoningHard problems that need careful thinking03Muse Spark 1.23 of 5 tests · 2 ties
- FactsGetting facts right instead of making them up03Muse Spark 1.23 of 3 tests
- Images and chartsUnderstanding pictures, charts and video01Muse Spark 1.21 of 1 test
- Following instructionsDoing exactly what it is asked01Muse Spark 1.21 of 1 test
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 52 of 3 tests · 1 tie
- CodingWriting and fixing software21Claude Sonnet 52 of 5 tests · 2 ties
- MathCompetition and research-level math10Claude Sonnet 51 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 51 of 1 test
Images and charts, 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 1.2 costs 54% 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 1.2 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+26.6points ahead
- Common-sense trick questionsSimpleBench+13.9points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+10.4points ahead
Where Claude Sonnet 5 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+7points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+3.2points ahead
- Reasons across sets of long documentsAA-LCR+3points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5
- LiveBench · CodingClaude Sonnet 5 by 3.280.777.5+3.2
- SciCodeMuse Spark 1.2 by 3.154.357.4+3.1
- LiveBench · Agentic CodingClaude Sonnet 5 by 1.859.457.6+1.8
- LMArena · WebDevtie15391532tie
- Terminal-Bench 2.1tie80.580.1tie
AgentsClaude Sonnet 5
- Terminal-Bench 4.0Claude Sonnet 5 by 714.17.1+7
- τ-Bench V3 · BankingClaude Sonnet 5 by 2.537.334.8+2.5
- GDPValtie48.348.9tie
ReasoningMuse Spark 1.2
- SimpleBenchMuse Spark 1.2 by 13.960.674.5+13.9
- Humanity's Last ExamMuse Spark 1.2 by 4.241.345.5+4.2
- LiveBench · ReasoningMuse Spark 1.2 by 1.388.790+1.3
- CritPttie16.917.7tie
- GPQA Diamondtie91.190.4tie
FactsMuse Spark 1.2
- SimpleQA VerifiedMuse Spark 1.2 by 26.633.760.3+26.6
- AA-Omniscience · Non-hallucinationMuse Spark 1.2 by 6.160.666.7+6.1
- AA-Omniscience · AccuracyMuse Spark 1.2 by 5.34045.4+5.3
Images and chartsMuse Spark 1.2
- LMArena · VisionMuse Spark 1.2 by 30 rating points12751305+30 rating
Following instructionsMuse Spark 1.2
- LiveBench · Instruction FollowingMuse Spark 1.2 by 10.463.974.3+10.4
Other results10 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.
- GDP (Surge AI)Claude Sonnet 5 by 65.681.616+65.6
- AA-OmniscienceMuse Spark 1.2 by 10.716.427.2+10.7
- DeepSWE 1.1Muse Spark 1.2 by 5.35459.3+5.3
- livebench_data_analysisMuse Spark 1.2 by 4.871.776.5+4.8
- GDPval-AA v2 EloMuse Spark 1.2 by 44 rating points15841628+44 rating
- livebench_languageMuse Spark 1.2 by 3.67578.6+3.6
- AA IntelligenceMuse Spark 1.2 by 1.438.239.6+1.4
- Artificial Analysis Coding Indextie71.572.2tie
- Code Arena (Elo)tie15411535tie
- AA Agentic Indextie44.344tie
Questions people ask
Which is better, Claude Sonnet 5 or Muse Spark 1.2?
Claude Sonnet 5 and Muse Spark 1.2 each win four of the eight areas we test. Claude Sonnet 5 wins coding, agents, math and long documents; Muse Spark 1.2 wins reasoning, facts, images and charts and following instructions. Muse Spark 1.2 costs 54% less.
Which is better for coding?
Claude Sonnet 5. It wins 2 of the 5 coding tests both models report; Muse Spark 1.2 wins 1, and 2 are ties.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Muse Spark 1.2 costs $1.25 and $4.25. That makes Muse Spark 1.2 about 54% cheaper for the same work.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.