#14Meta· 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
1490
LMArena — human blind votes
AA Index
62.0
Artificial Analysis composite
LiveBench
76.5
Contamination-resistant
GPQA
84.2%
Grad-level science reasoning
MMLU-Pro
85.6%
Broad knowledge
SWE-bench
68.8%
Real GitHub bugs (Verified)
Terminal-Bench
47.9%
Agentic shell tasks
ARC-AGI
16.8%
Abstract reasoning
Aider Polyglot
78.6%
Multi-language code editing
Speed
84 tok/s
Median output speed

Nearby on the leaderboard