Skip to main content
BenchLM
Data

Data as of November 4, 2026 · How the score is built

Superseded.Meta has newer models in this line:Muse Spark 1.3
SupersededProprietaryReasoning

Released Aug 5, 20261M contextMeta: Muse Spark 1.2 model page

Muse Spark 1.2

Decision readingMuse Spark 1.2 scores 65.4 out of 100 and ranks #28 of 216. This profile shows 9 source-displayable benchmark rows; its strongest eligible category is Agentic at #31. API pricing is $1.25 input and $4.25 output per million tokens, with cached input at $0.15.

Released Aug 5, 2026 — see all recent releases

Find alternativesCompare Muse Spark 1.2
Share or export
Share on XLinkedIn
Social cardBenchmarks CSVAPI/MCP query guide

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

65.4/100

field median 50.5#28 of 216 ranked models

Public

#28of 216

Verified #20 of 77

Price

$1.25input / $4.25 output

input median $0.75cached $0.15 · blended $2.75

Speed

154tok/s

field median 92 tok/sFirst token 28.37 s

Context

1Mtokens

field median 256,000Maximum output length is tracked separately

Strongest published evidence

Agentic ranks #31. Particularly useful for coding agents, browser research, and computer-use workflows.

Validate before choosing

9 published rows leave some tracked benchmark slots empty. Coding is its lowest eligible category at #37.

Source-linked · 9 displayable benchmark rows

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #31 of 135Percentile 78thWeight 22%3 benchmarksVerified
59.9
CodingRank #37 of 156Percentile 77thWeight 20%5 benchmarksVerified
52.8
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalWeight 12%0 benchmarksNot measured
Not measured
Knowledge3.0 points below Muse Spark 1.1Rank #33 of 179Percentile 82ndWeight 12%1 benchmarkVerified
64.7
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%0 benchmarksNot measured
Not measured
MathWeight 5%0 benchmarksNot measured
Not measured

An earlier release can outscore a newer one in a single category. The note under that category names the release and the gap.

9 of 797 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic3/3 verified
  2. Coding5/5 verified
  3. ReasoningNot measured
  4. MultimodalNot measured
  5. Knowledge1/1 verified
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. MathNot measured
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

Muse Spark 1.2 category percentile values

  • Agentic78th percentile
  • Coding77th percentile
  • ReasoningNot eligible
  • MultimodalNot eligible
  • Knowledge82nd percentile
  • MultilingualNot eligible
  • Instruction followingNot eligible
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#31/135
  2. Coding#37/156
  3. ReasoningNot ranked
  4. MultimodalNot ranked
  5. Knowledge#33/179
  6. MultilingualNot ranked
  7. Inst. FollowingNot ranked
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding5 rows
Coding benchmark values, best verified comparison, weight, and source status
DeepSWEScore59.3%Versus best verified row

Best verified: Muse Wonder Full · 79.0%

Gap19.7 behindWeight15% ref. weight
Provider exact
Meta: Muse Spark 1.2 model page
FrontierSWE v2Score12.0%Versus best verified row

Best verified: GPT-6 Astra · 65.5%

Gap53.5 behindWeight8% ref. weight
Benchmark exact
Proximal: FrontierSWE v2 leaderboard
VulcanBench v3Score87.0%Versus best verified row

Best verified: Grok 4.5 · 89.9%

Gap2.9 behindWeight3% ref. weight
Benchmark exact
VulcanBench Report 19: Muse Spark 1.2 effort study
Terminal-Bench 2.1Score82.9%Versus best verified row

Best verified: SWE-2 · 92.8%

Gap9.9 behindWeightScored in Agentic
Provider exact
Meta: Muse Spark 1.2 model page
SWE-bench (Vals)SWE-bench, Vals AI runScore86.6%Versus best verified row

Best verified: Claude Opus 5 · 97.0%

Gap10.4 behindWeightDisplay only
Verified
Vals AI: SWE-bench leaderboard
Agentic3 rows
Agentic benchmark values, best verified comparison, weight, and source status
Terminal-Bench 2.1Score82.9%Versus best verified row

Best verified: SWE-2 · 92.8%

Gap9.9 behindWeight8% ref. weight
Provider exact
Meta: Muse Spark 1.2 model page
Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI runScore69.7%Versus best verified row

Best verified: GPT-6 Astra · 87.3%

Gap17.6 behindWeight4% ref. weight
Verified
Vals AI: Terminal-Bench 2.1 leaderboard
MazeBenchMazeBench: visual spatial reasoning in a 3D open worldScore0%Versus best verified row

Best verified: GPT-6 Astra · 23%

Gap23 behindWeightDisplay only
Benchmark exact
MazeBench AI leaderboard (ASCII mode)
Knowledge1 row
Knowledge benchmark values, best verified comparison, weight, and source status
MMLU-Pro (Vals)MMLU-Pro, Vals AI runScore88.3%Versus best verified row

Best verified: Claude Fable 5.1 · 92.4%

Gap4.1 behindWeight6% ref. weight
Verified
Vals AI: MMLU Pro leaderboard

Bars run 0–100; the dark tick marks the best source-verified value

All 9 rows

What it costs to get this score

Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.

Current modelExplore all models

Muse Spark 1.2 · 65.4 score · $2.75 blended per million tokens

The chart opens on the current model. Scroll horizontally to inspect the full price axis.

405060708090100$0.10$0.50$1$5$10$25$50$100↘ frontierMuse Spark 1.2

Horizontal: blended price per million tokens, log scale · Vertical: public score

Price vs performance

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Apr 8, 2026

    Muse Spark

    Score 59.8 · Price not listed

  2. Jul 9, 2026

    Muse Spark 1.1

    Score 65.2 · Price not listed

  3. Aug 5, 2026 · you are here

    Muse Spark 1.2

    Score 65.4 · $1.25 / $4.25

  4. Sep 2, 2026

    Muse Spark 1.3

    Not publicly ranked · $1.25 / $4.25

1.2 · 1.2

Muse Spark 1.3Muse Spark 1.3Muse Spark 1.1 · 65.2Muse Spark · 59.8

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
muse-spark-1.2Meta: Muse Spark 1.2 model page
Context window
1MMeta: Muse Spark 1.2 model page
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not disclosed by the provider
Availability
Available through Meta Model API as muse-spark-1.2. Meta also offers a lower-priced muse-spark-1.2-contributor SKU whose data may be used to improve Meta products.
Cloud regions
Not tracked yet
Lifecycle
Superseded
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Published at $0.15 per million cached input tokensMeta: Muse Spark 1.2 model page
Self-host
Weights are not published
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

Muse Spark 1.2 ranks #28 of 216 on the public leaderboard with a score of 65.41/100. Its source-verified position is #20 of 77.

Muse Spark 1.2 is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Available through Meta Model API as muse-spark-1.2. Meta also offers a lower-priced muse-spark-1.2-contributor SKU whose data may be used to improve Meta products.

Muse Spark 1.2 sits in the Muse Spark family with Muse Spark 1.3, Muse Spark 1.1, Muse Spark. Its explicit predecessor is Muse Spark 1.1. 9 of 797 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Agentic at #31, while its lowest eligible position is Coding at #37. particularly useful for coding agents, browser research, and computer-use workflows.

Last updated November 4, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Where to run Muse Spark 1.2 by API

OpenRouter is the one host we track that publishes a per-token price for it. Prices read from each host’s own pages on October 20, 2026.

Inference hosts for Muse Spark 1.2 with input, output and cached-input prices per million tokens.
HostInput /1MOutput /1MCached /1MContext
OpenRouter$1.25$4.25$0.151.05M
Compare inference hosts

Questions

How does Muse Spark 1.2 perform overall in AI benchmarks?

Muse Spark 1.2 ranks #28 out of 216 models on the public BenchAlign leaderboard, with a score of 65.41/100. Its evidence status is Supported, and this profile shows 9 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is Muse Spark 1.2 good for knowledge and understanding?

Muse Spark 1.2 ranks #33 out of 179 eligible models for knowledge and understanding, with a public category score of 64.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Muse Spark 1.2 good for coding and programming?

Muse Spark 1.2 ranks #37 out of 156 eligible models for coding and programming, with a public category score of 52.8/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Muse Spark 1.2 good for agentic tool use and computer tasks?

Muse Spark 1.2 ranks #31 out of 135 eligible models for agentic tool use and computer tasks, with a public category score of 59.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Which sibling models are related to Muse Spark 1.2?

Muse Spark 1.2 belongs to the Muse Spark family. Related tracked variants include Muse Spark 1.3, Muse Spark 1.1, Muse Spark. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does Muse Spark 1.2 have full benchmark coverage on BenchLM?

No. Muse Spark 1.2 currently has 24 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Muse Spark 1.2?

Muse Spark 1.2 has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Watch Muse Spark 1.2 in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 6,100+ subscribers.

Compare Muse Spark 1.2 with every tracked model1007 comparisons