#06Meta· released 2026-09-02

Meta: Muse Spark 1.3.

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$1.25
Output $/1M
$4.25
Modality
text · image · video · file · audio
Arena Elo
1598
LMArena — human blind votes
AA Index
65.0
Artificial Analysis composite
LiveBench
87.6
Contamination-resistant
GPQA
89.9%
Grad-level science reasoning
MMLU-Pro
89.3%
Broad knowledge
SWE-bench
76.9%
Real GitHub bugs (Verified)
Terminal-Bench
68.9%
Agentic shell tasks
ARC-AGI
36.1%
Abstract reasoning
Aider Polyglot
83.7%
Multi-language code editing
Speed
64 tok/s
Median output speed

Profile

Meta: Muse Spark 1.3 is Meta's entry at position #6 on the current aggregated leaderboard. Its strongest signals are human preference voting, graduate-level science reasoning, real-world software engineering, and unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard