Muse Spark 1.3
ModelActiveby Meta · family “muse-spark”
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... (description from the OpenRouter listing)
in: textin: imagein: videoin: fileout: textReasoningTool useStructured output
Epoch Capabilities Index
156.9 #15 of 268
90% CI 154.7 – 159.4
Released
2 Sep 2026
Context window
1.05M tokens
Max output
944K tokens
Input $ / 1M tokens
$1.25
Output $ / 1M tokens
$4.25
Cached input $ / 1M
$0.15
Each benchmark shown separately with its own source
Benchmark results (4)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| Mystery Game Puzzles | games | 25.0% ±4.5 | 30% | max | 18 Sep 2026 | Epoch ↗ |
| FrontierMath-Tiers-1-3-v2-Private | math | 74.0% ±2.6 | 79% | max | 18 Sep 2026 | Epoch ↗ |
| FrontierMath-Tier-4-v2-Private | math | 46.3% ±7.9 | 47% | max | 18 Sep 2026 | Epoch ↗ |
| Chess Puzzles | games | 38.0% ±4.9 | 53% | max | 18 Sep 2026 | Epoch ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
Unchanged since first recorded on 27 Sep 2026 (OpenRouter listing); re-read on every data refresh, most recently 6h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates Muse Spark 1.3Epoch AI Benchmarking Hub
- Model launchMajorMeta releases Muse Spark 1.3Epoch AI Benchmarking Hub