BenchLeader

DeepSeek V4 Flash vs Muse Spark 1.3

Full profiles: DeepSeek V4 Flash (DeepSeek) and Muse Spark 1.3 (Meta): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, DeepSeek V4 Flash and Muse Spark 1.3 are neck and neck on quality (57.2 vs 61.6 on the BenchLeader Index, inside the ±9.1 margin), and DeepSeek V4 Flash is 7.6× cheaper at $0.262 vs $2.00 per 1M tokens blended. Choose DeepSeek V4 Flash for maths (62 vs 56) and fast first answers (0.7 s vs 2.6 s); choose Muse Spark 1.3 for knowledge (81 vs 55) and reasoning (71 vs 59), where it also streams ~1.5× faster.

Key facts (as of 16 Nov 2026)

  • DeepSeek V4 Flash scores 57.2 on the BenchLeader Index and Muse Spark 1.3 scores 61.6 (BenchLeader, 16 Nov 2026).
  • DeepSeek V4 Flash costs $0.262 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).
  • Muse Spark 1.3 streams ~1.5× faster than DeepSeek V4 Flash (Artificial Analysis, 7-day median, 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
MathsDeepSeek V4 Flash62 vs 56 category scoreMedium
ReasoningMuse Spark 1.371 vs 59 category scoreHigh
KnowledgeMuse Spark 1.381 vs 55 category scoreHigh
Chat quality (human preference)–Only DeepSeek V4 Flash has an Arena rating (62 category score)Not comparable
Lowest costDeepSeek V4 Flash$0.262 vs $2.00 per 1M blended; agentic coding session $0.011 vs $0.092–
Fastest first answerDeepSeek V4 Flash0.7 s (DeepSeek V4 Flash (high)) vs 2.6 s (Muse Spark 1.3) 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

  • DeepSeek V4 Flash (high) and Muse Spark 1.3 are neck and neck on quality (57.2 vs 61.6, within the ±9.1 margin).
  • DeepSeek V4 Flash (high) is stronger in maths.
  • Muse Spark 1.3 is stronger in knowledge, reasoning.
  • DeepSeek V4 Flash (high) is 7.6× cheaper ($0.262 vs $2.00 per 1M blended).
  • Muse Spark 1.3 streams 2.0× faster (163 vs 82 tokens per second).

At a glance

SpecDeepSeek V4 FlashMuse Spark 1.3
DeveloperDeepSeekMeta
Released31 Jul 20262 Sep 2026
Context window (tokens)1,048,5761,048,576
Compared atDeepSeek V4 Flash (high)Muse Spark 1.3
Open weightsYesNo
Price in / out / cached input per 1M$0.150 / $0.600 / $0.0030$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.

CategoryDeepSeek V4 Flash (high)Muse Spark 1.3Leader
Reasoning59.271.0Muse Spark 1.3
Coding55.0–not comparable
Agents & tools–61.3not comparable
Maths61.956.3DeepSeek V4 Flash
Knowledge54.881.2Muse Spark 1.3
Human preference62.0–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 avg75ReasoningMathsKnowledgeDeepSeek V4 Flash, Reasoning: 59.2DeepSeek V4 Flash, Maths: 61.9DeepSeek V4 Flash, Knowledge: 54.8Muse Spark 1.3, Reasoning: 71.0Muse Spark 1.3, Maths: 56.3Muse Spark 1.3, Knowledge: 81.2

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

Model, click to add or removeIndex

Where sources disagree

Across the 0 benchmarks both have, DeepSeek V4 Flash leads 0, Muse Spark 1.3 leads 0. Every overall index that rates both puts Muse Spark 1.3 ahead.

Overall indexDeepSeek V4 Flash (high)Muse Spark 1.3Leader
BenchLeader Index57.261.6neck and neck
Arena Text14391497†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.

MeasureDeepSeek V4 Flash (high)Muse Spark 1.3
Blended price per 1M tokens$0.262$2.00
Input / output per 1M$0.150 / $0.600$1.25 / $4.25
Cached input per 1M$0.0030$0.150
Price per task: chat reply$0.0002$0.0018
Price per task: summarize a 30-page report$0.0022$0.018
Price per task: code edit$0.0018$0.014
Price per task: agentic coding session$0.011$0.092
Price per task: structured extraction$0.0004$0.0034
Agentic coding session, input mostly cached$0.0048$0.043
Output speed82 tok/s163 tok/s
Time to first answer0.7 s2.6 s

Each model is compared at its best-ranked reasoning-effort setting. DeepSeek V4 Flash (high) scores 57.2 and takes 1 s to its first answer token; DeepSeek V4 Flash (max) scores 56.8 in 28 s, DeepSeek V4 Flash scores 53.8 in 1 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

143 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.

MetricPublisherDeepSeek V4 Flash (high)Muse Spark 1.3
BenchLeader IndexBenchLeader57.261.6
Coding scoreBenchLeader55.0–
Human preference scoreBenchLeader62.0–
Knowledge scoreBenchLeader54.881.2
Maths scoreBenchLeader61.956.3
Reasoning scoreBenchLeader59.271.0
Agents & tools scoreBenchLeader–61.3
Blended price $/MBenchLeader$0.262$2.00
Output speedBenchLeader82 tok/s163 tok/s
Time to first answerBenchLeader0.7 s2.6 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.0%†–
SimpleBenchSimpleBench61.1%†81.8%
Arena Hard PromptsArena (LMArena)14591517†
LiveBench 2.0 ReasoningLiveBench–89.7%†
LiveBench 1.0 ReasoningLiveBench86.6%†89.7%†
GPQA Diamond (AA)Artificial Analysis90.8%†93.5%†
Humanity's Last Exam (AA)Artificial Analysis38.5%†48.7%†
HLE-Diamond (AA)Artificial Analysis–33.7%†
GPQA Diamond (Vals)Vals AI89.9%–
Kagi LLM BenchmarkKagi LLM Benchmark52.2%†–
ARC-AGI-1ARC Prize87.0%–
ARC-AGI-2ARC Prize56.0%–
CritPtArtificial Analysis16.6%†24.9%†
CritPt v2 hard subset (AA)Artificial Analysis–48.0%†
MysteryMechanismVals AI–36.0%†
HLE-Diamond (Scale)Scale AI SEAL–25.4%
Arena ExpertArena (LMArena)14671521†
Chess PuzzlesEpoch AI Benchmarking Hub32.0%†37.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub34.0%†25.0%†
LMCAEpoch AI Benchmarking Hub41.7%†53.9%
DTBenchEpoch AI Benchmarking Hub90.9%†96.5%
ForecastBenchForecastBench–65.5%†
BTF-3Epoch AI Benchmarking Hub–14.1%†
Coding
SciCodeSciCode42.0%58.8%†
WeirdMLWeirdML57.0%–
Show all 143 benchmarks
MetricPublisherDeepSeek V4 Flash (high)Muse Spark 1.3
Coding
FrontierCodeCognition18.8%†–
Arena CodingArena (LMArena)14801534†
Arena WebDevArena (LMArena)15821655†
LiveBench 2.0 CodingLiveBench–84.4%†
LiveBench 1.0 CodingLiveBench75.0%†81.1%†
SciCode (AA)Artificial Analysis50.4%†58.8%†
LiveCodeBenchVals AI87.3%–
IOIVals AI32.7%56.6%†
SWE-bench (Vals)Vals AI88.8%–
Code MigrationVals AI38.6%47.4%†
ProgramBenchVals AI0.0%2.5%†
SWE-bench MultimodalVals AI–43.1%†
Vibe Code Bench 1-100Vals AI–20.5%†
Vibe Code Bench v1.1Vals AI74.7%85.9%†
MirrorCodeEpoch AI Benchmarking Hub–54.4%†
CursorBenchCursor–41.6%†
ALE-BenchEpoch AI Benchmarking Hub678.21688.3†
FrontierSWEEpoch AI Benchmarking Hub–25.8%†
WeirdML v3WeirdML–6.7%†
Terminal-Bench 4.0 (AA)Artificial Analysis12.1%†33.3%†
Terminal-Bench 2.1 (AA)Artificial Analysis78.7%†84.3%†
Startrise FrontendStartrise–74.7%
GameBench 2 OverallDuelLab GameBench 234.1†57.7
GameBench 2 by reasoning settingDuelLab GameBench 243.468.5†
Design Arena WebsiteDesign Arena1199†1353†
FrontierCode 1.1 (AA)Artificial Analysis–40.6%†
FrontierCode 2.0 (AA)Artificial Analysis–23.1%†
Agents & tools
Terminal-BenchTerminal-Bench–14.8%†
APEX-AgentsMercor–58.6%
Arena AgentArena (LMArena)–2.2†
LiveBench Long AgenticLiveBench–47.9%†
LiveBench BrowserLiveBench–30.9%†
LiveBench Agentic CodingLiveBench46.8%†64.1%†
Terminal-Bench 2.1 (Vals)Vals AI67.0%†79.0%†
HiL-BenchScale AI SEAL47.8%†66.9%
GDPval-AA v2.1Artificial Analysis1437†1681†
τ³-Banking (AA)Artificial Analysis39.4%†50.5%†
ITBench SRE (AA)Artificial Analysis–33.2%†
Analyst Agent (AA)Artificial Analysis–37.5%†
CUA-benchVals AI–5.8%†
CyberBenchVals AI72.1%72.7%†
Finance Agent v2Vals AI49.5%60.0%†
Harvey's Legal Agent Benchmark v1Vals AI8.3%23.8%†
Legal Research BenchVals AI30.3%55.3%†
SkillsBenchVals AI50.7%–
SREBenchVals AI–3.8%†
Tax Agent BenchVals AI28.1%42.4%†
Terminal-Bench 4.0 (Vals)Vals AI18.7%24.8%†
Terminal-Bench ScienceVals AI4.3%10.0%†
Arena Agent Task CompletionArena (LMArena)–3.7†
AutomationBenchArtificial Analysis54.0%†57.9%†
GDP.pdf (AA)Artificial Analysis11.0%†26.6%†
Harvey LAB-AA v1.1Harvey–8.9%†
AA-Briefcase v1.1Artificial Analysis1255†1581†
Design Arena AgenticDesign Arena–1283†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–10.9%†
CWE-Bench (AA)Artificial Analysis–60.8%†
DeepSec-Bench (AA)Artificial Analysis–12.5%†
CyberGym end-to-end (AA)Artificial Analysis–59.5%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub57.5%†74.0%†
FrontierMath Tier 4Epoch AI Benchmarking Hub24.4%†46.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub94.4%†99.2%†
ProofBenchVals AI56.0%†55.0%
LiveBench MathematicsLiveBench86.8%†96.0%†
AIME 2026MathArena95.8%†–
HMMT February 2026MathArena93.9%†–
MathArena ApexMathArena27.1%†–
Arena MathsArena (LMArena)14411506†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub33.6%†–
LiveBench 2.0 Data AnalysisLiveBench–79.6%†
LiveBench ResearchLiveBench–82.5%†
LiveBench 1.0 Data AnalysisLiveBench79.3%†79.6%†
AA-Omniscience v1.1Artificial Analysis–22.4†
MMLU-ProVals AI86.2%–
LegalBenchVals AI77.7%–
CorpFinVals AI61.9%–
TaxEvalVals AI70.7%–
PRBench FinanceScale AI SEAL–59.5%
PRBench LegalScale AI SEAL–61.6%
BioMysteryBenchVals AI64.4%–
Excel Modeling BenchmarkVals AI57.0%67.4%†
MedCodeVals AI41.4%–
MedScribeVals AI80.4%–
Access to Justice BenchmarkVals AI–72.2%†
Financial Coaching BenchVals AI–70.3%†
Immigration BenchVals AI–64.9%†
DrugDiscoveryBenchScale AI SEAL–62.2%†
GDP.pdfEpoch AI Benchmarking Hub–27.6%
AA-Omniscience v1.1: accuracyArtificial Analysis–38.0%†
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–74.8%†
Instruction following
LiveBench LanguageLiveBench79.2%†82.8%†
LiveBench Instruction FollowingLiveBench65.5%†78.0%†
Arena Instruction FollowingArena (LMArena)14341485†
Human preference
Arena TextArena (LMArena)14391497†
EQ-Bench Creative Writing v3EQ-Bench1559†1907
Arena Creative WritingArena (LMArena)14111468†
Arena Multi-turnArena (LMArena)14471493†
Arena Longer QueriesArena (LMArena)14491498†
Multimodal
Arena VisionArena (LMArena)–1310†
LiveBench DesignLiveBench–74.8%†
MMMU-ProArtificial Analysis–82.0%†
Humanity's Sixth SenseScale AI SEAL–37.4%†
GeoBenchGeoBench–86.0%
Code2Video-AAArtificial Analysis–1019†
AA-3DArtificial Analysis–1032†
Long context
AA-LCR v1.1Artificial Analysis79.7%†83.0%†
Arena DocumentArena (LMArena)–1474†
MLCRArtificial Analysis–13.9%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub154.4†158.2
LiveBench 2.0LiveBench–68.6%†
LiveBench 1.0LiveBench74.2%†81.6%†
AA Intelligence Index v5.0.1Artificial Analysis–36.6†
AA Intelligence Index v4.3.2Artificial Analysis34.3†48.1†
AA Progress Index v1Artificial Analysis309.4†324.5†
Vals RSI IndexVals AI–19.6%†
AA Cyber IndexArtificial Analysis–44.3†
Safety & honesty
DistressBenchScale AI SEAL–84.9%
Metadata
AA Openness IndexArtificial Analysis44.4†–

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

  • Muse Spark 1.3: BenchLeader Index 60.2 → 61.6.
  • DeepSeek V4 Flash (high): 1 score revision.
  • 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).
  • Muse Spark 1.3: BenchLeader Index 57.7 → 59.2.
  • Muse Spark 1.3: 4 score revisions.
  • Muse Spark 1.3: BenchLeader Index 58.2 → 57.7.
  • Muse Spark 1.3: 1 score revision.
  • DeepSeek V4 Flash (high): 1 score revision.

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

DeepSeek V4 Flash vs Muse Spark 1.3: questions

Is DeepSeek V4 Flash better than Muse Spark 1.3?
DeepSeek V4 Flash (high) and Muse Spark 1.3 are neck and neck on quality (57.2 vs 61.6, within the ±9.1 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
DeepSeek V4 Flash vs Muse Spark 1.3: which is cheaper, and will that change?
DeepSeek V4 Flash is cheaper today: $0.262 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, DeepSeek V4 Flash or Muse Spark 1.3?
Muse Spark 1.3 streams ~1.5× faster (163 vs 82 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Both accept 1,048,576 tokens of context.
Which has lower latency?
DeepSeek V4 Flash answers first: 0.7 s against 2.6 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.
More questions (1)
When was Muse Spark 1.3 released?
Muse Spark 1.3 was released on 2 Sep 2026.