whatmodel.sh / Muse Spark

Muse Spark

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Muse Spark is a closed-weights language model from Meta, released April 2026.

Catalogue identity notes

Comparison-only. Original Muse Spark, distinct from muse-spark-1-1/1-2/1-3. Epoch result CSVs list 'muse-spark' (Meta AI, release date 2026-04-08); arena entry 'muse-spark' (meta, Proprietary), first listed 2026-04-09.

75.0±1.9comparison only: no current run option verifiedfrom 5 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Muse Spark, out of 828 with a score, then more from Meta.

#modelscorewhereRAMreleased
42Grok 4.5 SpaceXAI (xAI)75±1api $3.00/M2026-07
43Muse Spark 1.1 Meta75±1api $2.00/M2026-07
44Muse Spark Meta75±2comparison only2026-04
45Step 5 Preview StepFun75±1comparison only
46Claude Sonnet 5 Anthropic75±1api $4.00/M2026-06
more from Meta
24Muse Spark 1.3 Meta77±1api $2.00/M2026-09
40Muse Spark 1.2 Meta75±1api $2.00/M2026-08
97Muse Glimmer 30B Meta70±1api $0.64/M +local~19GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #12 of 463 * · 33% of its score · 1 test

Beats GPT-6 Astra, GPT-6.1 Sol, Claude Sonnet 5.5 here, though they rank higher overall. Trails Claude Opus 4.6 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1489.3 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 368/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%blunt
math▁▂▃▅▇▅▅█▄▁▁▁ #78 of 462 * · 6.4% of its score · 1 test

Trails Granite 4.2 30B, INTELLECT-3, EXAONE 4.5 33B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
OTIS mock AIME 2024–202588.9% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 143/193very hard · avg 8.5%▇▇▇ 6.4%sharp · maxed out · noisy
vision & documents▁▁▃▃▂▃▅▄▇▇█▃ #14 of 182 * · 34% of its score · 2 tests

Beats Claude Sonnet 5.5, GPT-5.5, MiMo-V2.6-Pro here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
Arena vision (style controlled)1293.6 ✎▁▁▂▂▂▂▄▅▅▆██ beats 140/145avg 1068▇▇▇▇▇▇▇▇▇ 23%blunt
Arena document (style controlled)1467.3 ✎▁▁▃▃▄▃▇█▅▇▄▅ beats 22/37avg 1335▇▇▇▇ 11%blunt
other tests1 not in a task · 25% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond89.8% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 171/208hard · avg 40%▇▇▇▇▇▇▇▇▇▇ 25%sharp

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 67%, Epoch AI — internal evaluatio… 32%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%CC BY 4.0
Epoch AI — internal evaluations2▇▇▇▇▇▇▇▇▇▇ 32%CC BY 4.0
prior · pull toward the middle▇ 2%
weighted average= 75.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json