TL;DR
Muse Spark 1.1 had the higher raw planning mean, while Luna was the cheaper historical choice among close scores. On 29 frozen conversations published August 8, 2026, Muse scored 0.759 at $0.0229 per decision; Luna scored 0.731 at $0.0012. Their median response times were 9.6 and 8.6 seconds. Sample uncertainty matters, and this compares model versions rather than the Muse personal-agent product.
Planning models on 29 frozen conversations: published results
16-model campaign, 29 frozen conversations; 14 model rows shown in the public table. Published 2026-08-08. Each bar uses the original task scale. The original table retains all other dimensions and qualifications.
Show the table · 2 rows, 5 columns
Scroll sideways to compare all columns. Select a heading to sort.
| meta/muse-spark-1.1 | 0.759 | 0.079 | $0.0229 | 9.6s |
| openai/gpt-5.6-luna | 0.731 | 0.068 | $0.0012 | 8.6s |
No matching rows. Clear the filter to see all records.
16-model campaign, 29 frozen conversations; 14 model rows shown in the public table. Published 2026-08-08.
Which fits the tested job?
Muse Spark 1.1 had the higher raw planning mean; Luna was the cheaper recorded operating choice among close top scores. Test that cost and quality tradeoff on your own router; the highest mean alone does not establish a decisive quality win.
Planning models on 29 frozen conversations
Muse scored 0.759 (SE 0.079) versus Luna's 0.731 (SE 0.068). It cost $0.0229 versus $0.0012 per decision, with p50 9.6s versus 8.6s. The observed mean gap is small relative to the reported standard errors; that observation alone is not a paired significance test. This is Muse Spark the model, not the Muse personal-agent product.
Route a request and plan the work: follow the published task
A useful planner chooses the right kind of work before doing it. The complete customer conversations and system prompts remain private.
Published task summary
An incoming request and its existing conversation.
Choose whether to write a plan, call a catalog tool, ask for clarification or continue an existing agent.
Read what came back
A routing decision and plan. Every model receives the same saved conversation; the test compares that decision before fresh research begins.
Replay 29 frozen conversations across the model arms, then compare graded plan scores, billing and response time.
Results from tasks both models attempted
The tested model IDs are openai/gpt-5.6-luna and meta/muse-spark-1.1. Every result table below comes from a study in which both participated.
Compare the measured quality, historical billed cost and elapsed time within the same task and rubric.
Scores from different tasks are not combined into one winner score.
Planning models on 29 frozen conversations: read these measurements
Read the complete rubric, sample and billing notes
16-model campaign, 29 frozen conversations; 14 model rows shown in the public table
Route an incoming request: write a plan, call a catalog tool, ask for clarification or continue an existing agent.
Scoring
Top planning means were close at this sample size. The source's paired comparison with Opus was inconclusive.
Cost units
Cost is provider-billed dollars per decision. Prefix reuse can make it differ from list price multiplied by every input token.
Time units
p50 is median latency in seconds, not the duration of complete research.
Frozen conversation
A saved input kept identical across model arms so their decisions can be compared.
Standard error (SE)
An estimate of uncertainty around the sample mean. A small mean difference needs more evidence than the ranking alone.
No comments yet.