Skip to main content
AI Choice Engine

Model comparison

Mistral Large 3 vs Muse Spark 1.3

Mistral against Meta, compared on context, price, and attributed benchmark results.

Recorded profile verification October 2, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below

Mistral

Mistral Large 3

Frontier · Open weights

vs

Meta

Muse Spark 1.3

Frontier

AI model capability comparison
SpecificationMistral Large 3Muse Spark 1.3
ProviderMistralMeta
TierFrontierFrontier
Context window262KWinner: 1.05M
Max outputNot verifiedUnverifiedNot verifiedUnverified
Input / 1M tokensWinner: $0.50$1.25
Output / 1M tokensWinner: $1.50$4.25
WeightsOpenClosed
Parameters675B total / 41B active (sparse MoE)Not verifiedUnverified
Reasoning levelsNot verifiedUnverifiedminimal, low, medium, high, xhigh, max
Modalitiestext, imagetext, image, video, audio, pdf
LicenseApache 2.0Not verifiedUnverified
API model idmistral-large-2512muse-spark-1.3
ReleasedDecember 2, 2025September 2, 2026
Artificial Analysis Intelligence Index · source date Mistral Large 3: 2026-10-019Not verifiedUnverified
Artificial Analysis Intelligence Index [max] · source date Muse Spark 1.3: 2026-10-01Not verifiedUnverified48
GPQA Diamond · source date Mistral Large 3: 2026-09-2668Not verifiedUnverified
DeepSWE 1.1 · source date Muse Spark 1.3: 2026-09-02Not verifiedUnverified75.4

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Pricing tiers

Mistral Large 3: Mistral first-party API $0.50/$1.50 per MTok; cached input $0.05. The 675B-total / 41B-active multimodal checkpoint declares Apache 2.0. Regional hosting is endpoint-specific.

Muse Spark 1.3: Meta Standard $1.25/$4.25 per MTok, cached $0.15; prompts/completions are not used for training. Contributor uses a distinct SKU at $0.10/$0.20, cached $0.002, and permits training on prompts/completions. No long-context premium. Search grounding adds $2.50 per 1,000 queries.

FrontierOpen weightsRecord checked October 2, 2026

Mistral Large 3

Mistral's December 2025 multimodal 675B/41B sparse MoE with a 256K context; Medium 3.5 is a separate dense model with configurable reasoning.

Best for

  • Open-weight deployments
  • Multimodal EU-hosted inference
  • Balanced frontier work

Watch out

The publisher describes Large 3 as not a dedicated reasoning model and documents vision limitations. It advertises FP8 deployment on a B200/H200 node or a separate NVFP4 checkpoint on H100/A100 nodes; this is not a guarantee for every serving setup. A separate hard output cap is not verified. Confirm regional residency on the actual endpoint.

FrontierRecord checked October 2, 2026

Muse Spark 1.3

Muse Spark 1.3 is Meta's September 2026 frontier refresh with a 1M-token context for coding and agent workflows.

Best for

  • Long-horizon coding agents
  • Frontier quality below frontier pricing
  • Meta ecosystem

Watch out

Max effort is Standard Spark 1.3 only; Contributor and Spark 1.2 lack it. None returns HTTP 400; omitted effort is model-determined. Reasoning counts toward output budget and billing. Spark 1.3 audio may degrade; Meta directs audio work to 1.2 or Voice Transcribe. Standard 3,000 RPM/4M TPM versus Contributor 100 RPM/3M TPM quotas apply per team. Exact output cap and parameter count remain unknown. Meta's 75.4% DeepSWE max/mini-swe-agent report is separate from independent xhigh observations.

When the cheaper one wins

Mistral Large 3 is cheaper on output at $1.50 per million tokens against $4.25 for Muse Spark 1.3 — about 2.8×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: Medium

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 2/5 core specs verified on both sides — Not published for at least one side: max output, parameter count, reasoning levels.
  • No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
  • Verified within the last 90 days — Older of the two catalog checks was 24 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? Mistral Large 3 · Muse Spark 1.3

Common questions

Mistral Large 3 vs Muse Spark 1.3

Answered from the verified figures on this page rather than general guidance.

Is Mistral Large 3 or Muse Spark 1.3 cheaper for input?
Mistral Large 3 is cheaper at $0.50 per million input tokens, against $1.25 for Muse Spark 1.3 — roughly 2.5× the price. Estimate both input and output token volume for your workload. These are base rates; Mistral Large 3: Mistral first-party API $0.50/$1.50 per MTok; cached input $0.05. The 675B-total / 41B-active multimodal checkpoint declares Apache 2.0. Regional hosting is endpoint-specific. Muse Spark 1.3: Meta Standard $1.25/$4.25 per MTok, cached $0.15; prompts/completions are not used for training. Contributor uses a distinct SKU at $0.10/$0.20, cached $0.002, and permits training on prompts/completions. No long-context premium. Search grounding adds $2.50 per 1,000 queries.
Is Mistral Large 3 or Muse Spark 1.3 cheaper for output?
Mistral Large 3 is cheaper at $1.50 per million output tokens, against $4.25 for Muse Spark 1.3 — roughly 2.8× the price. Estimate both input and output token volume for your workload. These are base rates; Mistral Large 3: Mistral first-party API $0.50/$1.50 per MTok; cached input $0.05. The 675B-total / 41B-active multimodal checkpoint declares Apache 2.0. Regional hosting is endpoint-specific. Muse Spark 1.3: Meta Standard $1.25/$4.25 per MTok, cached $0.15; prompts/completions are not used for training. Contributor uses a distinct SKU at $0.10/$0.20, cached $0.002, and permits training on prompts/completions. No long-context premium. Search grounding adds $2.50 per 1,000 queries.
Which has the larger context window, Mistral Large 3 or Muse Spark 1.3?
Muse Spark 1.3 accepts 1.05M tokens against 262K for Mistral Large 3. This only matters if you routinely send very long documents or large codebases.
Should I use Mistral Large 3 or Muse Spark 1.3?
Both are classified in our frontier tier; this editorial grouping does not imply equal capability. Mistral Large 3 is a candidate for open-weight deployments; Muse Spark 1.3 is a candidate for long-horizon coding agents. Compare accuracy, tool reliability, latency and cost on representative tasks.
Can I self-host Mistral Large 3 or Muse Spark 1.3?
Mistral Large 3 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. Muse Spark 1.3 is a closed model whose supported access paths are controlled by its provider.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: Mistral Large 3 costs $0.50 per 1M tokens versus $1.25 for Muse Spark 1.3 — a 2.5x difference at the headline tier.
  • Context: Muse Spark 1.3 takes 1.05M against 262K for Mistral Large 3 — only decisive if your prompts approach the smaller window.
  • Deployment: Mistral Large 3 publishes weights you can self-host; the other is API-only.
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.