Skip to content

Meta · Chat

Muse Spark Open

Meta 🇺🇸ChatMuse familyOpen weights. One of its sources says the weights are publicly available.
From Venice's listing:
Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.
llminfo IQ
136.3
Market median price
$2.00 blended / 1M
Max context
1M
Listings
40

Evidence and sources

🤗 meta-models/Muse-Spark-Open-816B-A42B822B params Model architecture, as its sources state it llminfo IQ 136.3, ranked among chat models. From 58 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 113.5, 95% interval 105–122. From 7 benchmark families across 3 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedFair value (49.6). Costs per task about what its benchmark results predict. From 20 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 15 Oct 2026Maker HQ: US (according to Meta's own website)
All rankings: #110 on OpenRouter this month #117 on OpenRouter this week #153 on OpenRouter today #310 on NanoGPT recentlySources: LMArena data, Models.dev data, AI/ML API data, Morpheus Inference Marketplace data, Venice.ai data, llminfo researchPrimary data from LMArena from Models.dev: weights availability from AI/ML API: primary mode from Morpheus Inference Marketplace: architecture, parameter count from Venice.ai: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchAudio input

Listings

 Flowdotaccounts/fireworks/models/muse-spark-openSource: FlowDot data1M$0.50$0.50——
 Abliteratedllmmuse-spark-openSource: Models.dev data1M$1.125cache read $0.135$3.825——
 Eden AIInference by Fireworks AIfireworks_ai/accounts/fireworks/models/muse-spark-openSource: Models.dev data1M$1.25cache read $0.15$4.25——
 Fastroutermeta/muse-spark-openSource: FastRouter data1M$1.25cache read $0.15$4.25——
 Kilometa/muse-spark-openSources: Kilo AI Gateway data, Models.dev data1M$1.25cache read $0.15$4.25——
 LlmgatewayInference by Fireworks AIaccounts/fireworks/models/muse-spark-openSource: LLMGateway dataNot published by the provider$1.25cache read $0.15$4.25——
 NanoGPTmeta/muse-spark-openSources: Models.dev data, NanoGPT1M$1.25cache read $0.15$4.25——
 Nous Portalmeta/muse-spark-openSource: Nous Portal Inference Gateway data1M$1.25cache read $0.15$4.25——
 OpenRouterInference by Basetenmeta/muse-spark-open · fp4Source: OpenRouter data docs1M$1.25cache read $0.15$4.25260215ms
 Vercelmeta/muse-spark-openSources: Models.dev data, Vercel AI Gateway data1M$1.25cache read $0.15$4.25——

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

GDPval-AASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
JobBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MCP AtlasSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports · Oct 2026
15 Oct 2026 version · 90-day results
Across 6 providers lowest 72.3% median 73.7% highest 75.5%OpenRouter's automatic routing 75.7%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Modal
  • Nebius
  • Fireworks
  • Together
  • Makora
  • BaseTen

Coding

SciCodeSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
ValsSource: Vals AI

Reasoning

WorldVQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond7 results
Source: OpenRouter benchmark exports
15 Oct 2026 version · 90-day results
Across 6 providers lowest 89.7% median 90.1% highest 91%OpenRouter's automatic routing 90.2%
Show results from 6 providers and OpenRouter's automatic routingHide results from 6 providers and OpenRouter's automatic routing
  • Modal
  • Makora
  • OpenRouter's automatic routing
  • BaseTen
  • Fireworks
  • Together
  • Nebius

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs · Oct 2026

Human preference

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Math

MathArenaSource: MathArena data

General

Vision

SimpleVQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

ValsSource: Vals AI

Data credits: Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence)

Also known as: accounts/fireworks/models/muse-spark-open, baseten/meta-models/muse-spark-open, fireworks/muse-spark-open, fireworks_ai/accounts/fireworks/models/muse-spark-open, meta-models/muse-spark-open, meta/muse-spark-open, muse spark open, muse-spark-open-max, nebius/meta-models/muse-spark-open, together-ai/muse-spark-open

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works