GPT-5.6 Luna vs Muse Spark 1.1
Wins 2 of 8 areas
Agents · Long documents
Wins 3 of 8 areas
Facts · Images and charts · Following instructions
Muse Spark 1.1 wins more areas, narrowly.GPT-5.6 Luna is cheaper and better at agents.
Scores updated · 33 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.
- FactsGetting facts right instead of making them up03Muse Spark 1.13 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Muse Spark 1.12 of 2 tests
- Following instructionsDoing exactly what it is asked01Muse Spark 1.11 of 1 test
- AgentsCarrying out multi-step tasks on its own21GPT-5.6 Luna2 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10GPT-5.6 Luna1 of 1 test
- CodingWriting and fixing software33Even3 each
- ReasoningHard problems that need careful thinking22Even2 each
- 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.
GPT-5.6 Luna costs 75% 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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+42.6points ahead
- Short factual questions, answered correctlySimpleQA Verified+16.8points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+10.1points ahead
Where GPT-5.6 Luna pulls ahead
- Real work tasks from 44 professionsGDPVal+12.4points ahead
- Reasons across sets of long documentsAA-LCR+6points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+5.7points ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- LiveBench · Agentic CodingMuse Spark 1.1 by 10.148.458.5+10.1
- LiveBench · CodingGPT-5.6 Luna by 5.782.977.2+5.7
- SciCodeMuse Spark 1.1 by 5.253.658.8+5.2
- Terminal-Bench 2.1GPT-5.6 Luna by 380.977.9+3
- LMArena · WebDevMuse Spark 1.1 by 23 rating points15191542+23 rating
- SWE-bench ProGPT-5.6 Luna by 1.262.761.5+1.2
AgentsGPT-5.6 Luna
- GDPValGPT-5.6 Luna by 12.44835.6+12.4
- OSWorld-VerifiedMuse Spark 1.1 by 8.272.680.8+8.2
- Terminal-Bench 4.0GPT-5.6 Luna by 5.511.66.1+5.5
- τ-Bench V3 · Bankingtie31.131.8tie
ReasoningEven
- Humanity's Last ExamMuse Spark 1.1 by 6.739.546.2+6.7
- CritPtGPT-5.6 Luna by 5.520.615.1+5.5
- LiveBench · ReasoningMuse Spark 1.1 by 2.185.687.7+2.1
- GPQA DiamondGPT-5.6 Luna by 1.391.189.8+1.3
FactsMuse Spark 1.1
- AA-Omniscience · Non-hallucinationMuse Spark 1.1 by 42.67.450+42.6
- SimpleQA VerifiedMuse Spark 1.1 by 16.84157.8+16.8
- AA-Omniscience · AccuracyMuse Spark 1.1 by 9.442.752+9.4
Images and chartsMuse Spark 1.1
- CharXiv (RQ)Muse Spark 1.1 by 5.782.788.4+5.7
- LMArena · VisionMuse Spark 1.1 by 36 rating points12571293+36 rating
Following instructionsMuse Spark 1.1
- LiveBench · Instruction FollowingMuse Spark 1.1 by 9.560.169.6+9.5
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.
- AA-OmniscienceMuse Spark 1.1 by 38.4-10.328.1+38.4
- ToolathlonMuse Spark 1.1 by 22.253.475.6+22.2
- GDPval-AA v2 EloGPT-5.6 Luna by 203 rating points15841381+203 rating
- AA Agentic IndexGPT-5.6 Luna by 15.242.727.5+15.2
- DeepSWE 1.1GPT-5.6 Luna by 146753+14
- Toolathlon VerifiedMuse Spark 1.1 by 7.767.975.6+7.7
- livebench_data_analysisGPT-5.6 Luna by 5.47872.5+5.4
- AA IntelligenceGPT-5.6 Luna by 3.637.333.7+3.6
- HealthBench ProfessionalMuse Spark 1.1 by 3.655.759.3+3.6
- livebench_languageMuse Spark 1.1 by 1.772.674.3+1.7
- Artificial Analysis Coding Indextie71.471.3tie
Questions people ask
Which is better, GPT-5.6 Luna or Muse Spark 1.1?
Muse Spark 1.1 wins three of the eight areas we test: facts, images and charts and following instructions. GPT-5.6 Luna wins agents and long documents, and costs 75% less. They are level on coding, reasoning and math.
Which is better for coding?
Neither. They win 3 coding tests each of the 6 both models report.
Which is cheaper?
GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens; Muse Spark 1.1 costs $1.25 and $4.25. That makes GPT-5.6 Luna about 75% cheaper for the same work.
How do you compare the two?
We use the 33 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 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.