BenchLeader

Kimi K3.1 Pro vs Muse Spark 1.1

Full profiles: Kimi K3.1 Pro (Moonshot AI) and Muse Spark 1.1 (Meta): every benchmark, price and rank.

Updated · Data from 11 sources

As of 10 Nov 2026, Kimi K3.1 Pro and Muse Spark 1.1 are neck and neck on quality (61.2 vs 62.2 on the BenchLeader Index, inside the ±6.6 margin), and Muse Spark 1.1 is 2.0× cheaper at $2.00 vs $4.00 per 1M tokens blended. Choose Kimi K3.1 Pro for agents & tools (67 vs 51), maths (73 vs 61), and multimodal (66 vs 64); choose Muse Spark 1.1 for fast first answers (1.7 s vs 161.8 s) and reasoning (68 vs 60), knowledge (69 vs 62), and coding (66 vs 60), where it also streams 3×+ faster.

Key facts (as of 10 Nov 2026)

  • Kimi K3.1 Pro scores 61.2 on the BenchLeader Index and Muse Spark 1.1 scores 62.2 (BenchLeader, 10 Nov 2026).
  • Kimi K3.1 Pro costs $4.00 per 1M tokens blended (list price, 10 Nov 2026).
  • Muse Spark 1.1 costs $2.00 per 1M tokens blended (list price, 10 Nov 2026).
  • Muse Spark 1.1 streams 3×+ faster than Kimi K3.1 Pro (Artificial Analysis, 7-day median, 10 Nov 2026).
  • Of the 6 benchmarks both models have, Kimi K3.1 Pro leads 6 (BenchLeader, 10 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
CodingMuse Spark 1.166 vs 60 category score; SciCode 58.8% vs 60.8%Medium
Agents & tool useKimi K3.1 Pro67 vs 51 category score; APEX-Agents 65.5% vs 31.8%High
MathsKimi K3.1 Pro73 vs 61 category score; ProofBench 91.0% vs 39.0%High
ReasoningMuse Spark 1.168 vs 60 category scoreHigh
KnowledgeMuse Spark 1.169 vs 62 category scoreHigh
Images and other mediaKimi K3.1 Pro66 vs 64 category scoreMedium
Chat quality (human preference)–Only Muse Spark 1.1 has an Arena rating (65 category score)Not comparable
Lowest costMuse Spark 1.1$2.00 vs $4.00 per 1M blended; agentic coding session $0.092 vs $0.160–
Fastest first answerMuse Spark 1.11.7 s (Muse Spark 1.1) vs 161.8 s (Kimi K3.1 Pro) 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

  • Kimi K3.1 Pro and Muse Spark 1.1 are neck and neck on quality (61.2 vs 62.2, within the ±6.6 margin).
  • Kimi K3.1 Pro is stronger in agents & tools, composite, long context, maths, multimodal.
  • Muse Spark 1.1 is stronger in coding, knowledge, reasoning, human preference, instruction following.
  • Muse Spark 1.1 is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
  • Muse Spark 1.1 streams 5.8× faster (185 vs 32 tokens per second).

At a glance

SpecKimi K3.1 ProMuse Spark 1.1
DeveloperMoonshot AIMeta
Released23 Oct 20269 Jul 2026
Context window (tokens)1,048,5761,048,576
Compared atKimi K3.1 ProMuse Spark 1.1
Open weightsYesNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.200$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.

CategoryKimi K3.1 ProMuse Spark 1.1Leader
Reasoning59.667.8Muse Spark 1.1
Coding59.866.2Muse Spark 1.1
Agents & tools67.151.0Kimi K3.1 Pro
Maths73.461.3Kimi K3.1 Pro
Knowledge61.569.4Muse Spark 1.1
Instruction following–70.3not comparable
Human preference–64.5not comparable
Multimodal66.463.6Kimi K3.1 Pro
Long context68.0–not comparable
Composite54.8–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 avg75ReasoningCodingAgents & toolsMathsKnowledgeMultimodalKimi K3.1 Pro, Reasoning: 59.6Kimi K3.1 Pro, Coding: 59.8Kimi K3.1 Pro, Agents & tools: 67.1Kimi K3.1 Pro, Maths: 73.4Kimi K3.1 Pro, Knowledge: 61.5Kimi K3.1 Pro, Multimodal: 66.4Muse Spark 1.1, Reasoning: 67.8Muse Spark 1.1, Coding: 66.2Muse Spark 1.1, Agents & tools: 51.0Muse Spark 1.1, Maths: 61.3Muse Spark 1.1, Knowledge: 69.4Muse Spark 1.1, Multimodal: 63.6

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

ModelIndex

Where sources disagree

Across the 6 benchmarks both have, Kimi K3.1 Pro leads 6, Muse Spark 1.1 leads 0. Every overall index that rates both puts Muse Spark 1.1 ahead.

Overall indexKimi K3.1 ProMuse Spark 1.1Leader
BenchLeader Index61.262.2neck and neck
Arena Text1483†1491Muse Spark 1.1

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.

MeasureKimi K3.1 ProMuse Spark 1.1
Blended price per 1M tokens$4.00$2.00
Input / output per 1M$2.00 / $10.00$1.25 / $4.25
Cached input per 1M$0.200$0.150
Price per task: chat reply$0.0038$0.0018
Price per task: summarize a 30-page report$0.030$0.018
Price per task: code edit$0.027$0.014
Price per task: agentic coding session$0.160$0.092
Price per task: structured extraction$0.0060$0.0034
Agentic coding session, input mostly cached$0.079$0.043
Cost per benchmark task (AA Index)$3.68–
Output tokens per task (AA Index)72k–
Of which reasoning44k–
Time per task (AA Index)38 min–
Output speed32 tok/s185 tok/s
Time to first answer161.8 s1.7 s
Time to a complete answer397.6 s–

Each model is compared at its best-ranked reasoning-effort setting. Kimi K3.1 Pro scores 61.2 and takes 162 s to its first answer token; Kimi K3.1 Pro (max) scores 60.4 in 162 s. Muse Spark 1.1 scores 62.2 and takes 2 s to its first answer token; Muse Spark 1.1 (xhigh) scores 59.6 in 13 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

127 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.

MetricPublisherKimi K3.1 ProMuse Spark 1.1
BenchLeader IndexBenchLeader61.262.2
Agents & tools scoreBenchLeader67.151.0
Coding scoreBenchLeader59.866.2
Composite scoreBenchLeader54.8–
Knowledge scoreBenchLeader61.569.4
Long context scoreBenchLeader68.0–
Maths scoreBenchLeader73.461.3
Multimodal scoreBenchLeader66.463.6
Reasoning scoreBenchLeader59.667.8
Human preference scoreBenchLeader–64.5
Instruction following scoreBenchLeader–70.3
Blended price $/MBenchLeader$4.00$2.00
Output speedBenchLeader32 tok/s185 tok/s
Time to first answerBenchLeader161.8 s1.7 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
Arena Hard PromptsArena (LMArena)1501†1511
LiveBench 2.0 ReasoningLiveBench91.1%–
LiveBench 1.0 ReasoningLiveBench–87.7%†
GPQA Diamond (AA)Artificial Analysis–89.8%†
Humanity's Last Exam (AA)Artificial Analysis52.5%46.2%†
HLE-Diamond (AA)Artificial Analysis37.3%–
GPQA Diamond (Vals)Vals AI–91.2%†
CritPtArtificial Analysis24.6%15.1%†
CritPt v2 hard subset (AA)Artificial Analysis49.5%–
MysteryMechanismVals AI26.1%†–
Chess PuzzlesEpoch AI Benchmarking Hub–34.0%†
LMCAEpoch AI Benchmarking Hub57.6%†49.9%†
DTBenchEpoch AI Benchmarking Hub93.3%†94.4%†
Coding
SciCodeSciCode60.8%58.8%
Arena CodingArena (LMArena)1526†1533
Arena WebDevArena (LMArena)1688†1542
LiveBench 2.0 CodingLiveBench67.8%–
LiveBench 1.0 CodingLiveBench–77.2%†
LiveCodeBenchVals AI–85.9%†
IOIVals AI81.9%†–
SWE-bench (Vals)Vals AI–82.0%†
SWE-Bench ProScale AI SEAL–61.5%
Code MigrationVals AI–31.1%†
ProgramBenchVals AI–0.0%†
Vibe Code Bench v1.1Vals AI84.9%†72.2%†
Show all 127 benchmarks
MetricPublisherKimi K3.1 ProMuse Spark 1.1
Coding
SWE-Bench Pro (private)Scale AI SEAL–61.5%
SWE Atlas: Codebase QnAScale AI SEAL–42.2%†
SWE Atlas: Test WritingScale AI SEAL–41.5%†
Surface Evolver BenchEpoch AI Benchmarking Hub–52.5%†
DeepSWE v1.1Epoch AI Benchmarking Hub–53.3%
ALE-BenchEpoch AI Benchmarking Hub1932.8†–
Terminal-Bench 4.0 (AA)Artificial Analysis67.2%6.1%†
Terminal-Bench 2.1 (AA)Artificial Analysis–77.9%†
Startrise FrontendStartrise82.5%–
GameBench 2 OverallDuelLab GameBench 278.2–
GameBench 2 by reasoning settingDuelLab GameBench 284.0†–
Design Arena WebsiteDesign Arena13201266
FrontierCode 1.1 (AA)Artificial Analysis47.1%–
FrontierCode 2.0 (AA)Artificial Analysis25.4%–
Agents & tools
APEX-AgentsMercor65.5%31.8%
Arena AgentArena (LMArena)5.2†-7.9
LiveBench Long AgenticLiveBench38.7%–
LiveBench BrowserLiveBench75.9%–
LiveBench Agentic CodingLiveBench–58.5%†
Terminal-Bench 2.1 (Vals)Vals AI–69.3%†
MCP AtlasScale AI SEAL–88.1%
τ³-bench Bankingτ²-bench–40.5%†
GDPval-AA v2.1, normalised scoreArtificial Analysis67.3%–
GDPval-AA v2.1Artificial Analysis1861–
τ³-Banking (AA)Artificial Analysis–31.8%†
Analyst Agent (AA)Artificial Analysis38.8%–
Finance Agent v2Vals AI–57.2%†
Finance Agent v2.1Vals AI61.5%†–
Harvey's Legal Agent Benchmark v1.1Vals AI11.7%†–
Harvey's Legal Agent Benchmark v1Vals AI–20.0%†
Legal Research BenchVals AI37.5%†38.0%†
SkillsBenchVals AI–59.2%†
SREBenchVals AI27.1%†–
Tax Agent BenchVals AI24.9%†–
Terminal-Bench 4.0 (Vals)Vals AI63.6%†–
Terminal-Bench ScienceVals AI31.4%†–
Time Horizon Index: KSPVals AI–1.7%†
GBAEvalEpoch AI Benchmarking Hub–7.9%
Vending-Bench 2Andon Labs–6520.5
AutomationBenchArtificial Analysis73.3%38.9%†
GDP.pdf (AA)Artificial Analysis31.4%14.4%†
AA-Briefcase v1.1Artificial Analysis1674–
Design Arena AgenticDesign Arena12811165
Terminal-Bench-Science 0.1 (AA)Artificial Analysis34.3%–
CWE-Bench (AA)Artificial Analysis60.8%–
DeepSec-Bench (AA)Artificial Analysis36.7%–
CyberGym end-to-end (AA)Artificial Analysis94.7%–
Maths
ProofBenchVals AI91.0%39.0%
LiveBench MathematicsLiveBench–87.1%†
Arena MathsArena (LMArena)–1493
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–57.8%
LiveBench 2.0 Data AnalysisLiveBench79.1%–
LiveBench ResearchLiveBench82.1%–
LiveBench 1.0 Data AnalysisLiveBench–72.5%†
AA-Omniscience v1.1Artificial Analysis29.9–
MMLU-ProVals AI–88.7%†
LegalBenchVals AI–85.0%†
CorpFinVals AI–71.3%†
TaxEvalVals AI–79.7%†
PRBench FinanceScale AI SEAL–55.0%
PRBench LegalScale AI SEAL–57.0%
MultiNRCScale AI SEAL–65.6%
BioMysteryBenchVals AI75.6%†–
Excel Modeling BenchmarkVals AI–56.4%†
Excel Modeling Benchmark v1.1Vals AI70.0%†–
MedScribeVals AI–88.9%†
Public Benefits Bench v1.1Vals AI–61.3%†
GDP.pdfEpoch AI Benchmarking Hub–15.0%
AA-Omniscience v1.1: accuracyArtificial Analysis48.9%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis62.7%–
Instruction following
LiveBench LanguageLiveBench–74.3%†
LiveBench Instruction FollowingLiveBench–69.6%†
MultiChallengeScale AI SEAL–75.3%
Arena Instruction FollowingArena (LMArena)1485†1473
Human preference
Arena TextArena (LMArena)1483†1491
EQ-Bench 4EQ-Bench–1244
Arena Creative WritingArena (LMArena)1457†1443
Arena Multi-turnArena (LMArena)1473†1497
Arena Longer QueriesArena (LMArena)1488†1480
Multimodal
Arena VisionArena (LMArena)–1292
LiveBench DesignLiveBench73.7%–
MMMU-ProArtificial Analysis83.9%–
MMMU-Pro (Vals)Vals AI–86.6%†
MortgageTaxVals AI–66.1%†
VTBScale AI SEAL–44.8%
AA-3DArtificial Analysis1112–
Long context
AA-LCR v1.1Artificial Analysis86.3%77.7%†
Arena DocumentArena (LMArena)–1480
MLCRArtificial Analysis38.3%7.2%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub162.0154.8
LiveBench 2.0LiveBench68.7%–
LiveBench 1.0LiveBench–75.3%†
AA Intelligence Index v5.0Artificial Analysis46.5–
AA Intelligence Index v4.3.2Artificial Analysis55.133.7†
AA Progress Index v1Artificial Analysis340.7302.7†
Vals IndexVals AI62.5†–
Vals Finance IndexVals AI56.0%†–
Vals Science IndexVals AI44.4%†–
Vals Multimodal IndexVals AI–66.7%†
AA Cyber IndexArtificial Analysis64.1–
Safety & honesty
FORTRESSScale AI SEAL–12.4%
Metadata
AA Openness IndexArtificial Analysis33.3–

Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Kimi K3.1 Pro: 2 new results (APEX-Agents, Epoch Capabilities Index).
  • Kimi K3.1 Pro: BenchLeader Index 61.8 → 61.2.
  • Kimi K3.1 Pro: 5 score revisions.
  • Kimi K3.1 Pro: BenchLeader Index 61.3 → 61.8.
  • Muse Spark 1.1: 1 score revision.
  • Kimi K3.1 Pro: 1 new result (GameBench 2 Overall); 1 score revision.
  • Kimi K3.1 Pro: 1 score revision.
  • Kimi K3.1 Pro: BenchLeader Index 59.3 → 61.3.
  • Kimi K3.1 Pro: 3 new results (SciCode, ProofBench, Startrise Frontend).
  • Muse Spark 1.1: 2 score revisions.

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

Kimi K3.1 Pro vs Muse Spark 1.1: questions

Is Kimi K3.1 Pro better than Muse Spark 1.1?
Kimi K3.1 Pro and Muse Spark 1.1 are neck and neck on quality (61.2 vs 62.2, within the ±6.6 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 10 Nov 2026, so check the category scores for your use.
Kimi K3.1 Pro vs Muse Spark 1.1: which is cheaper, and will that change?
Muse Spark 1.1 is cheaper today: $2.00 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Kimi K3.1 Pro or Muse Spark 1.1 better for coding?
Muse Spark 1.1 scores higher in coding (66 vs 60 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 60.8% for Kimi K3.1 Pro against 58.8% for Muse Spark 1.1.
Which is faster, Kimi K3.1 Pro or Muse Spark 1.1?
Muse Spark 1.1 streams 3×+ faster (185 vs 32 output tokens per second, Artificial Analysis 7-day median).
Is Kimi K3.1 Pro or Muse Spark 1.1 better for agents and tool use?
Kimi K3.1 Pro scores higher in agentic tasks (67 vs 51 on the category index, where 50 is average). On APEX-Agents, the top shared agents & tools benchmark, it is 65.5% for Kimi K3.1 Pro against 31.8% for Muse Spark 1.1.
More questions (4)
Which is better for long documents?
Both accept 1,048,576 tokens of context.
Which has lower latency?
Muse Spark 1.1 answers first: 1.7 s against 161.8 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 Kimi K3.1 Pro vs Muse Spark 1.1?
Across the 6 benchmarks both have, Kimi K3.1 Pro leads 6, Muse Spark 1.1 leads 0. Every overall index that rates both puts Muse Spark 1.1 ahead.
When was Kimi K3.1 Pro released?
Kimi K3.1 Pro was released on 23 Oct 2026.