#17Meta· released 2026-07-16

Meta: Muse Spark 1.1.

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$1.25
Output $/1M
$4.25
Modality
text · image · video · file · audio

Benchmarks

How these are aggregated →
Arena Elo
1485
LMArena — human blind votes
AA Index
56.0
Artificial Analysis composite
LiveBench
74.5
Contamination-resistant
GPQA
81.2%
Grad-level science reasoning
MMLU-Pro
80.2%
Broad knowledge
SWE-bench
63.8%
Real GitHub bugs (Verified)
Terminal-Bench
42.9%
Agentic shell tasks
ARC-AGI
13.1%
Abstract reasoning
Aider Polyglot
79.6%
Multi-language code editing
Speed
92 tok/s
Median output speed

Nearby on the leaderboard