Terminal-Bench 4.0
muse-code1.4.1
Reasoning effort xhigh
Tested model identity
Muse Spark 1.3meta/muse-spark-1.3Pass rate14.55%
95% CI 11.61%–17.49%
n = 330Checked
metaListed Sep 2, 2026
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...
Context window1M
Max output943.7K
Provider endpoints2
Benchmark results0
Agent runs1
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Model + harness
All agent results ↗Agent runs
muse-code
Access & cost
2 quotesPrices across providers
OpenRouter
Catalog quote- Input
- $1.25
- Output
- $4.25
- Cached input
- $0.15
- Input
- $1.25
- Output
- $4.25
- Cached input
- $0.15
Web search $0.0025/search
Model specifications
- Developer
- meta
- Modality
- Language
- Context
- 1,048,576 tokens
- Maximum output
- 943,718 tokens
- Weights
- Not reported
- Provider listed
- Sep 2, 2026
- First discovered
- Oct 16, 2026
More from meta
View all ↗metaReleased 3 days ago
Meta: Muse Spark Open
OpenRouter lists a 1,048,576-token context and up to 943,718 output tokens for this open-weight model aimed at agentic coding.
1M contextImage inputAudio input
metaListed 5 days ago
Meta: Muse Wonder
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
1M contextImage inputAudio inputNo reported score
No reported score
metaListed Sep 11
Meta: Muse Voice Transcribe 1.0
Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and language…
Audio inputNo reported score
No reported score
metaListed Sep 2
Meta: Muse Spark 1.3 Contributor
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is…
1M contextImage inputVideo inputNo reported score
No reported score