modelbenchmark.io

Muse Spark 1.1

Meta · muse-spark-1-1

Compare

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-04-08
Knowledge cutoff
Retires
Open weights
no
Input
text, image, video, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.25
Output
$4.25
Cache read
$0.15
Cache write
$1.25

Quality

2 benchmarks · 2 sources

Composite
83rd
percentile of 334 scored models
Rank
58 / 334
±0.23 sd
Evidence
2 × 2
one source, or fewer than 3 benchmarks
Effort range
one configuration only
knowledge82nd1/1 bench
general50th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SimpleQA Verified57.8 ±1.6defaultEpoch AI2026-08-31
LiveBench76.0xhigh · 23 runsLiveBench2026-06-25

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 12 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
abacus$1.25$4.25$0.151M32K
empiriolabs$1.25$4.25$1.001M131K
kilo$1.25$4.25$0.151M944K
llmgateway$1.25$4.25$0.151M131K
llmgateway-providers$1.25$4.25$0.151M131K
merge-gateway$1.25$4.25$0.151M262K
meta$1.25$4.25$0.151M131K
nano-gpt$1.25$4.25$0.151M66K
openrouter$1.25$4.25$0.151M944K
orcarouter$1.25$4.25$0.151M131K
pioneer$1.25$4.25$0.15$1.251M131K
vercel$1.25$4.25$0.151M1M

More from Meta

most-hosted first