BenchLeader

Mistral Large 4 vs Muse Spark 1.3

Full profiles: Mistral Large 4 (Mistral AI) and Muse Spark 1.3 (Meta): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, Muse Spark 1.3 is ahead of Mistral Large 4 on quality (61.6 vs 52.9 on the BenchLeader Index), but Mistral Large 4 is 1.9× cheaper at $1.05 vs $2.00 per 1M tokens blended. Muse Spark 1.3 leads in every category we measure both in.

Key facts (as of 16 Nov 2026)

  • Mistral Large 4 scores 52.9 on the BenchLeader Index and Muse Spark 1.3 scores 61.6 (BenchLeader, 16 Nov 2026).
  • Mistral Large 4 costs $1.05 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Spark 1.3 costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 5 benchmarks both models have, Muse Spark 1.3 leads 5 (BenchLeader, 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
Agents & tool useMuse Spark 1.361 vs 49 category scoreHigh
MathsMuse Spark 1.356 vs 54 category score; ProofBench 55.0% vs 10.0%Medium
ReasoningMuse Spark 1.371 vs 46 category score; LMCA 53.9% vs 35.8%High
KnowledgeMuse Spark 1.381 vs 41 category scoreHigh
Chat quality (human preference)–Only Mistral Large 4 has an Arena rating (60 category score)Not comparable
Lowest costMistral Large 4$1.05 vs $2.00 per 1M blended; agentic coding session $0.050 vs $0.092–
Fastest first answerMuse Spark 1.32.6 s (Muse Spark 1.3) vs 40.9 s (Mistral Large 4) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Muse Spark 1.3 leads on quality: 61.6 vs 52.9.
  • Muse Spark 1.3 is stronger in agents & tools, knowledge, maths, reasoning.
  • Mistral Large 4 is 1.9× cheaper ($1.05 vs $2.00 per 1M blended).
  • Muse Spark 1.3 streams 1.7× faster (163 vs 97 tokens per second).

At a glance

SpecMistral Large 4Muse Spark 1.3
DeveloperMistral AIMeta
Released6 Oct 20262 Sep 2026
Context window (tokens)1,048,5761,048,576
Compared atMistral Large 4Muse Spark 1.3
Open weightsYesNo
Price in / out / cached input per 1M$0.700 / $2.10 / $0.070$1.25 / $4.25 / $0.150

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryMistral Large 4Muse Spark 1.3Leader
Reasoning46.271.0Muse Spark 1.3
Coding53.8–not comparable
Agents & tools48.861.3Muse Spark 1.3
Maths54.256.3Muse Spark 1.3
Knowledge40.781.2Muse Spark 1.3
Human preference59.7–not comparable
Multimodal58.0–not comparable
Long context65.3–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningAgents & toolsMathsKnowledgeMistral Large 4, Reasoning: 46.2Mistral Large 4, Agents & tools: 48.8Mistral Large 4, Maths: 54.2Mistral Large 4, Knowledge: 40.7Muse Spark 1.3, Reasoning: 71.0Muse Spark 1.3, Agents & tools: 61.3Muse Spark 1.3, Maths: 56.3Muse Spark 1.3, Knowledge: 81.2

Not drawn, measured for fewer than two of these models: Coding, Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 5 benchmarks both have, Mistral Large 4 leads 0, Muse Spark 1.3 leads 5. Every overall index that rates both puts Muse Spark 1.3 ahead.

Overall indexMistral Large 4Muse Spark 1.3Leader
BenchLeader Index52.961.6Muse Spark 1.3
AA Intelligence Index v5.0.125.336.6†Muse Spark 1.3
Arena Text14201497†Muse Spark 1.3

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureMistral Large 4Muse Spark 1.3
Blended price per 1M tokens$1.05$2.00
Input / output per 1M$0.700 / $2.10$1.25 / $4.25
Cached input per 1M$0.070$0.150
Price per task: chat reply$0.0009$0.0018
Price per task: summarize a 30-page report$0.0097$0.018
Price per task: code edit$0.0074$0.014
Price per task: agentic coding session$0.050$0.092
Price per task: structured extraction$0.0018$0.0034
Agentic coding session, input mostly cached$0.022$0.043
Cost per benchmark task (AA Index)$4.21–
Output tokens per task (AA Index)135k–
Of which reasoning102k–
Time per task (AA Index)23 min–
Output speed97 tok/s163 tok/s
Time to first answer40.9 s2.6 s
Time to a complete answer, last measured 13 Nov 2026119.0 s–

Each model is compared at its best-ranked reasoning-effort setting. Mistral Large 4 scores 52.9 and takes 41 s to its first answer token; Mistral Large 4 (high) scores 48.3 in 45 s, Mistral Large 4 (medium) scores 45.9 in 27 s. Muse Spark 1.3 scores 61.6 and takes 3 s to its first answer token; Muse Spark 1.3 (max) scores 60.6 in 31 s, Muse Spark 1.3 (xhigh) scores 58.1 in 11 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

142 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherMistral Large 4Muse Spark 1.3
BenchLeader IndexBenchLeader52.961.6
Agents & tools scoreBenchLeader48.861.3
Coding scoreBenchLeader53.8–
Human preference scoreBenchLeader59.7–
Knowledge scoreBenchLeader40.781.2
Long context scoreBenchLeader65.3–
Maths scoreBenchLeader54.256.3
Multimodal scoreBenchLeader58.0–
Reasoning scoreBenchLeader46.271.0
Blended price $/MBenchLeader$1.05$2.00
Output speedBenchLeader97 tok/s163 tok/s
Time to first answerBenchLeader40.9 s2.6 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub88.1%†–
SimpleBenchSimpleBench–81.8%
Arena Hard PromptsArena (LMArena)14531517†
LiveBench 2.0 ReasoningLiveBench85.2%†89.7%†
LiveBench 1.0 ReasoningLiveBench83.9%†89.7%†
GPQA Diamond (AA)Artificial Analysis–93.5%†
Humanity's Last Exam (AA)Artificial Analysis35.0%48.7%†
HLE-Diamond (AA)Artificial Analysis15.1%33.7%†
CritPtArtificial Analysis10.6%24.9%†
CritPt v2 hard subset (AA)Artificial Analysis24.5%48.0%†
MysteryMechanismVals AI12.2%†36.0%†
HLE-Diamond (Scale)Scale AI SEAL–25.4%
Arena ExpertArena (LMArena)14641521†
Chess PuzzlesEpoch AI Benchmarking Hub33.0%†37.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub17.0%†25.0%†
LMCAEpoch AI Benchmarking Hub35.8%53.9%
DTBenchEpoch AI Benchmarking Hub88.2%96.5%
ForecastBenchForecastBench–65.5%†
BTF-3Epoch AI Benchmarking Hub–14.1%†
Coding
SciCodeSciCode54.2%58.8%†
FrontierCodeCognition39.4%†–
Arena CodingArena (LMArena)14841534†
Arena WebDevArena (LMArena)15651655†
LiveBench 2.0 CodingLiveBench79.4%†84.4%†
LiveBench 1.0 CodingLiveBench77.2%†81.1%†
Show all 142 benchmarks
MetricPublisherMistral Large 4Muse Spark 1.3
Coding
IOIVals AI45.3%†56.6%†
Code MigrationVals AI30.6%†47.4%†
ProgramBenchVals AI–2.5%†
SWE-bench MultimodalVals AI33.1%†43.1%†
Vibe Code Bench 1-100Vals AI14.3%†20.5%†
Vibe Code Bench v1.1Vals AI78.4%†85.9%†
SWE Atlas v1.1Scale AI SEAL45.2%–
SWE Atlas v1.1: Codebase QnAScale AI SEAL61.3%–
SWE Atlas v1.1: Test WritingScale AI SEAL40.0%–
SWE Atlas v1.1: RefactoringScale AI SEAL34.3%–
MirrorCodeEpoch AI Benchmarking Hub40.0%†54.4%†
Surface Evolver BenchEpoch AI Benchmarking Hub28.1%–
CursorBenchCursor–41.6%†
ALE-BenchEpoch AI Benchmarking Hub1213.21688.3†
FrontierSWEEpoch AI Benchmarking Hub–25.8%†
WeirdML v3WeirdML4.5%†6.7%†
Terminal-Bench 4.0 (AA)Artificial Analysis26.8%33.3%†
Terminal-Bench 2.1 (AA)Artificial Analysis–84.3%†
Startrise FrontendStartrise–74.7%
GameBench 2 OverallDuelLab GameBench 2–57.7
GameBench 2 by reasoning settingDuelLab GameBench 257.6†68.5†
Design Arena WebsiteDesign Arena12581353†
FrontierCode 1.1 (AA)Artificial Analysis41.5%40.6%†
FrontierCode 2.0 (AA)Artificial Analysis13.6%23.1%†
Agents & tools
Terminal-BenchTerminal-Bench27.6%†14.8%†
APEX-AgentsMercor51.6%†58.6%
Arena AgentArena (LMArena)-5.42.2†
LiveBench Long AgenticLiveBench24.7%†47.9%†
LiveBench BrowserLiveBench17.4%†30.9%†
LiveBench Agentic CodingLiveBench57.2%†64.1%†
Terminal-Bench 2.1 (Vals)Vals AI–79.0%†
HiL-BenchScale AI SEAL–66.9%
GDPval-AA v2.1, normalised scoreArtificial Analysis46.1%–
GDPval-AA v2.1Artificial Analysis14311681†
τ³-Banking (AA)Artificial Analysis–50.5%†
ITBench SRE (AA)Artificial Analysis–33.2%†
Analyst Agent (AA)Artificial Analysis–37.5%†
CUA-benchVals AI–5.8%†
CyberBenchVals AI–72.7%†
Finance Agent v2Vals AI54.7%†60.0%†
Finance Agent v2.1Vals AI61.4%†–
Harvey's Legal Agent Benchmark v1.1Vals AI17.5%†–
Harvey's Legal Agent Benchmark v1Vals AI15.8%†23.8%†
Legal Research BenchVals AI31.7%†55.3%†
SREBenchVals AI–3.8%†
Tax Agent BenchVals AI30.4%†42.4%†
Terminal-Bench 4.0 (Vals)Vals AI27.8%†24.8%†
Terminal-Bench ScienceVals AI–10.0%†
Arena Agent Task CompletionArena (LMArena)-4.73.7†
AutomationBenchArtificial Analysis59.9%57.9%†
GDP.pdf (AA)Artificial Analysis18.6%26.6%†
Harvey LAB-AA v1.1Harvey3.1%8.9%†
AA-Briefcase v1.1Artificial Analysis13931581†
Design Arena AgenticDesign Arena–1283†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis4.8%10.9%†
CWE-Bench (AA)Artificial Analysis50.8%60.8%†
DeepSec-Bench (AA)Artificial Analysis16.0%12.5%†
CyberGym end-to-end (AA)Artificial Analysis81.7%59.5%†
MKA (AA)Artificial Analysis35.1%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub58.6%†74.0%†
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%†46.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub98.3%†99.2%†
ProofBenchVals AI10.0%55.0%
LiveBench MathematicsLiveBench93.6%†96.0%†
Arena MathsArena (LMArena)14591506†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub20.0%†–
LiveBench 2.0 Data AnalysisLiveBench76.6%†79.6%†
LiveBench ResearchLiveBench80.3%†82.5%†
LiveBench 1.0 Data AnalysisLiveBench76.5%†79.6%†
AA-Omniscience v1.1Artificial Analysis-7.522.4†
PRBench FinanceScale AI SEAL–59.5%
PRBench LegalScale AI SEAL–61.6%
BioMysteryBenchVals AI67.0%†–
Excel Modeling BenchmarkVals AI56.2%†67.4%†
Excel Modeling Benchmark v1.1Vals AI69.0%†–
MedCodeVals AI40.7%†–
MedScribeVals AI80.4%†–
Access to Justice BenchmarkVals AI–72.2%†
Financial Coaching BenchVals AI–70.3%†
Immigration BenchVals AI63.7%†64.9%†
DrugDiscoveryBenchScale AI SEAL–62.2%†
GDP.pdfEpoch AI Benchmarking Hub–27.6%
AA-Omniscience v1.1: accuracyArtificial Analysis23.9%38.0%†
AA-Omniscience v1.1: non-hallucinationArtificial Analysis58.7%74.8%†
Instruction following
LiveBench LanguageLiveBench49.6%†82.8%†
LiveBench Instruction FollowingLiveBench64.8%†78.0%†
Arena Instruction FollowingArena (LMArena)14181485†
Human preference
Arena TextArena (LMArena)14201497†
EQ-Bench Creative Writing v3EQ-Bench–1907
Arena Creative WritingArena (LMArena)13591468†
Arena Multi-turnArena (LMArena)14291493†
Arena Longer QueriesArena (LMArena)14201498†
Multimodal
Arena VisionArena (LMArena)12441310†
LiveBench DesignLiveBench76.3%†74.8%†
MMMU-ProArtificial Analysis76.4%82.0%†
Humanity's Sixth SenseScale AI SEAL–37.4%†
GeoBenchGeoBench–86.0%
Furniture AssemblyEpoch AI Benchmarking Hub20.8%†–
VIALS-AAHandshake AI20.5%†–
Code2Video-AAArtificial Analysis9311019†
AA-3DArtificial Analysis8821032†
Long context
AA-LCR v1.1Artificial Analysis81.3%83.0%†
Arena DocumentArena (LMArena)–1474†
MLCRArtificial Analysis7.8%13.9%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub154.6158.2
LiveBench 2.0LiveBench60.3%†68.6%†
LiveBench 1.0LiveBench71.8%†81.6%†
AA Intelligence Index v5.0.1Artificial Analysis25.336.6†
AA Intelligence Index v4.3.2Artificial Analysis38.448.1†
AA Progress Index v1Artificial Analysis312.4324.5†
Vals Finance IndexVals AI56.9%†–
Vals RSI IndexVals AI–19.6%†
Vals Legal IndexVals AI65.6%†–
AA Cyber IndexArtificial Analysis49.544.3†
Safety & honesty
FORTRESSScale AI SEAL23.1%–
DistressBenchScale AI SEAL77.0%84.9%
Metadata
AA Openness IndexArtificial Analysis38.9†–

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Mistral Large 4: BenchLeader Index 52.2 → 52.9.
  • Muse Spark 1.3: BenchLeader Index 60.2 → 61.6.
  • Mistral Large 4: 1 new result (GDPval-AA v2.1).
  • Mistral Large 4: 1 score revision.
  • Mistral Large 4: 2 score revisions.
  • Muse Spark 1.3: 1 score revision.
  • Muse Spark 1.3: BenchLeader Index 59.2 → 60.2.
  • Muse Spark 1.3: 2 new results (SimpleBench, GeoBench).
  • Mistral Large 4: 6 score revisions.
  • Mistral Large 4: BenchLeader Index 52.7 → 52.2.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Mistral Large 4 vs Muse Spark 1.3: questions

Is Muse Spark 1.3 better than Mistral Large 4?
Muse Spark 1.3 leads on quality: 61.6 vs 52.9. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Mistral Large 4 vs Muse Spark 1.3: which is cheaper, and will that change?
Mistral Large 4 is cheaper today: $1.05 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Which is faster, Mistral Large 4 or Muse Spark 1.3?
Muse Spark 1.3 streams faster (163 vs 97 output tokens per second, Artificial Analysis 7-day median).
Is Mistral Large 4 or Muse Spark 1.3 better for agents and tool use?
Muse Spark 1.3 scores higher in agentic tasks (61 vs 49 on the category index, where 50 is average).
Which is better for long documents?
Both accept 1,048,576 tokens of context.
More questions (3)
Which has lower latency?
Muse Spark 1.3 answers first: 2.6 s against 40.9 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Mistral Large 4 vs Muse Spark 1.3?
Across the 5 benchmarks both have, Mistral Large 4 leads 0, Muse Spark 1.3 leads 5. Every overall index that rates both puts Muse Spark 1.3 ahead.
When was Mistral Large 4 released?
Mistral Large 4 was released on 6 Oct 2026.