BenchLeader

Kimi K3 vs Muse Spark 1.2

Full profiles: Kimi K3 (Moonshot AI) and Muse Spark 1.2 (Meta): every benchmark, price and rank.

Updated · Data from 13 sources

As of 12 Nov 2026, Kimi K3 and Muse Spark 1.2 are neck and neck on quality (62.0 vs 61.6 on the BenchLeader Index, inside the ±5.9 margin), and Muse Spark 1.2 is 3.0× cheaper at $2.00 vs $6.00 per 1M tokens blended. Choose Kimi K3 for coding (64 vs 55), long context (69 vs 64), and agents & tools (58 vs 56); choose Muse Spark 1.2 for fast first answers (7.9 s vs 78.8 s) and reasoning (68 vs 59), knowledge (65 vs 60), and maths (67 vs 64), where it also streams 3×+ faster.

Key facts (as of 12 Nov 2026)

  • Kimi K3 scores 62.0 on the BenchLeader Index and Muse Spark 1.2 scores 61.6 (BenchLeader, 12 Nov 2026).
  • Kimi K3 costs $6.00 per 1M tokens blended (list price, 12 Nov 2026).
  • Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 12 Nov 2026).
  • Muse Spark 1.2 streams 3×+ faster than Kimi K3 (Artificial Analysis, 7-day median, 12 Nov 2026).
  • Of the 48 benchmarks both models have, Kimi K3 leads 36 (BenchLeader, 12 Nov 2026).
  • On Arena WebDev, Kimi K3 is rated 1658 and Muse Spark 1.2 1534 (LMArena, as published by 12 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
CodingKimi K364 vs 55 category score; Arena WebDev 1658 vs 1534High
Agents & tool useKimi K358 vs 56 category score; τ³-Banking (AA) 46.0% vs 34.9%Medium
MathsMuse Spark 1.267 vs 64 category score; Arena Maths 1490 vs 1503Medium
ReasoningMuse Spark 1.268 vs 59 category score; Arena Hard Prompts 1515 vs 1515High
KnowledgeMuse Spark 1.265 vs 60 category score; SimpleQA Verified 60.3% vs 50.6%Medium
Long documentsKimi K369 vs 64 category score; AA-LCR v1.1 88.7% vs 79.0%Medium
Images and other mediaMuse Spark 1.265 vs 63 category scoreMedium
Chat quality (human preference)Either68 vs 69 on Arena votesEither
Lowest costMuse Spark 1.2$2.00 vs $6.00 per 1M blended; agentic coding session $0.092 vs $0.240–
Fastest first answerMuse Spark 1.27.9 s (Muse Spark 1.2 (xhigh)) vs 78.8 s (Kimi K3 (max)) 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 (max) and Muse Spark 1.2 (xhigh) are neck and neck on quality (62.0 vs 61.6, within the ±5.9 margin).
  • Kimi K3 (max) is stronger in agents & tools, coding, long context.
  • Muse Spark 1.2 (xhigh) is stronger in human preference, knowledge, maths, multimodal, reasoning.
  • Muse Spark 1.2 (xhigh) is 3.0× cheaper ($2.00 vs $6.00 per 1M blended).
  • Muse Spark 1.2 (xhigh) streams 4.5× faster (204 vs 46 tokens per second).

At a glance

SpecKimi K3Muse Spark 1.2
DeveloperMoonshot AIMeta
Released16 Jul 20265 Aug 2026
Context window (tokens)1,048,5761,048,576
Compared atKimi K3 (max)Muse Spark 1.2 (xhigh)
Open weightsYesNo
Price in / out / cached input per 1M$3.00 / $15.00 / $0.300$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 (max)Muse Spark 1.2 (xhigh)Leader
Reasoning58.868.3Muse Spark 1.2
Coding64.354.8Kimi K3
Agents & tools58.355.5Kimi K3
Maths64.267.2Muse Spark 1.2
Knowledge59.664.5Muse Spark 1.2
Human preference67.968.7level
Multimodal63.065.3Muse Spark 1.2
Long context69.264.2Kimi K3

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 & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceKimi K3, Reasoning: 58.8Kimi K3, Coding: 64.3Kimi K3, Agents & tools: 58.3Kimi K3, Maths: 64.2Kimi K3, Knowledge: 59.6Kimi K3, Long context: 69.2Kimi K3, Multimodal: 63.0Kimi K3, Human preference: 67.9Muse Spark 1.2, Reasoning: 68.3Muse Spark 1.2, Coding: 54.8Muse Spark 1.2, Agents & tools: 55.5Muse Spark 1.2, Maths: 67.2Muse Spark 1.2, Knowledge: 64.5Muse Spark 1.2, Long context: 64.2Muse Spark 1.2, Multimodal: 65.3Muse Spark 1.2, Human preference: 68.7

Not drawn, measured for fewer than two of these models: Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 48 benchmarks both have, Kimi K3 leads 36, Muse Spark 1.2 leads 12. Every overall index that rates both puts Muse Spark 1.2 ahead.

Overall indexKimi K3 (max)Muse Spark 1.2 (xhigh)Leader
BenchLeader Index62.061.6neck and neck
Arena Text14871494Muse Spark 1.2

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 (max)Muse Spark 1.2 (xhigh)
Blended price per 1M tokens$6.00$2.00
Input / output per 1M$3.00 / $15.00$1.25 / $4.25
Cached input per 1M$0.300$0.150
Price per task: chat reply$0.0057$0.0018
Price per task: summarize a 30-page report$0.045$0.018
Price per task: code edit$0.041$0.014
Price per task: agentic coding session$0.240$0.092
Price per task: structured extraction$0.0090$0.0034
Agentic coding session, input mostly cached$0.118$0.043
Output speed46 tok/s204 tok/s
Time to first answer78.8 s7.9 s
Time to a complete answer156.1 s24.3 s

Each model is compared at its best-ranked reasoning-effort setting. Kimi K3 (max) scores 62.0 and takes 79 s to its first answer token; Kimi K3 scores 59.2 in 1 s, Kimi K3 (low) scores 53.7 in 11 s. Muse Spark 1.2 (xhigh) scores 61.6 and takes 8 s to its first answer token. 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

148 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 (max)Muse Spark 1.2 (xhigh)
BenchLeader IndexBenchLeader62.061.6
Agents & tools scoreBenchLeader58.355.5
Coding scoreBenchLeader64.354.8
Human preference scoreBenchLeader67.968.7
Knowledge scoreBenchLeader59.664.5
Long context scoreBenchLeader69.264.2
Maths scoreBenchLeader64.267.2
Multimodal scoreBenchLeader63.065.3
Reasoning scoreBenchLeader58.868.3
Blended price $/MBenchLeader$6.00$2.00
Output speedBenchLeader46 tok/s204 tok/s
Time to first answerBenchLeader78.8 s7.9 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.1%–
SimpleBenchSimpleBench60.7%74.5%†
Arena Hard PromptsArena (LMArena)15151515
LiveBench 2.0 ReasoningLiveBench90.7%†–
LiveBench 1.0 ReasoningLiveBench90.7%†90.0%
GPQA Diamond (AA)Artificial Analysis93.5%90.4%
Humanity's Last Exam (AA)Artificial Analysis46.9%45.5%
HLE-Diamond (AA)Artificial Analysis26.9%–
GPQA Diamond (Vals)Vals AI92.9%†–
ARC-AGI-1ARC Prize94.5%–
ARC-AGI-2ARC Prize60.4%–
CritPtArtificial Analysis23.4%17.7%
CritPt v2 hard subset (AA)Artificial Analysis40.5%–
Chess PuzzlesEpoch AI Benchmarking Hub36.0%27.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub26.0%–
LMCAEpoch AI Benchmarking Hub52.7%48.4%
DTBenchEpoch AI Benchmarking Hub91.2%94.7%
ForecastBenchForecastBench64.2%–
Coding
SciCodeSciCode59.5%57.4%
WeirdMLWeirdML82.6%60.3%
FrontierCodeCognition44.2%†–
Arena CodingArena (LMArena)15371543
Arena WebDevArena (LMArena)16581534
LiveBench 2.0 CodingLiveBench53.1%†–
LiveBench 1.0 CodingLiveBench81.5%†77.5%
Show all 148 benchmarks
MetricPublisherKimi K3 (max)Muse Spark 1.2 (xhigh)
Coding
LiveCodeBenchVals AI87.2%–
IOIVals AI48.9%21.8%
SWE-bench (Vals)Vals AI93.4%†86.6%
Code MigrationVals AI16.1%29.9%
Code Migration v1.1Vals AI28.6%–
ProgramBenchVals AI2.0%†0.5%
SWE-bench MultimodalVals AI44.2%–
Vibe Code Bench 1-100Vals AI18.2%–
Vibe Code Bench v1.1Vals AI85.0%79.1%
MirrorCodeEpoch AI Benchmarking Hub54.4%–
Surface Evolver BenchEpoch AI Benchmarking Hub93.0%–
DeepSWE v1.1Epoch AI Benchmarking Hub68.5%54.9%
ALE-BenchEpoch AI Benchmarking Hub1524.5–
FrontierSWEEpoch AI Benchmarking Hub25.9%12.0%
Terminal-Bench 4.0 (AA)Artificial Analysis12.6%7.1%
Terminal-Bench 2.1 (AA)Artificial Analysis85.0%80.2%
Startrise FrontendStartrise79.8%†70.3%†
GameBench 2 OverallDuelLab GameBench 247.6†51.4†
GameBench 2 by reasoning settingDuelLab GameBench 244.857.3
Design Arena WebsiteDesign Arena1329†1309†
FrontierCode 1.1 (AA)Artificial Analysis43.6%–
FrontierCode 2.0 (AA)Artificial Analysis10.9%†–
Agents & tools
APEX-AgentsMercor47.8%†45.4%†
Arena AgentArena (LMArena)0.6-8.2
LiveBench Long AgenticLiveBench36.0%†–
LiveBench BrowserLiveBench75.2%†–
LiveBench Agentic CodingLiveBench62.2%†57.6%
Terminal-Bench 2.1 (Vals)Vals AI80.9%†69.7%
MCP AtlasScale AI SEAL82.3%–
HiL-BenchScale AI SEAL42.7%†–
τ³-bench Bankingτ²-bench37.1%–
τ³-Banking (AA)Artificial Analysis46.0%34.9%
ITBench SRE (AA)Artificial Analysis47.7%–
Analyst Agent (AA)Artificial Analysis38.8%–
APEX-Agents (AA)Artificial Analysis41.3%–
CyberBenchVals AI75.2%69.5%
Finance Agent v2Vals AI53.1%60.6%
Finance Agent v2.1Vals AI60.0%–
Harvey's Legal Agent Benchmark v1.1Vals AI12.9%–
Harvey's Legal Agent Benchmark v1Vals AI12.9%25.4%
Legal Research BenchVals AI46.1%43.8%
SkillsBenchVals AI–53.0%
SREBenchVals AI–0.0%
Tax Agent BenchVals AI33.4%32.8%
Terminal-Bench 4.0 (Vals)Vals AI17.2%6.1%
Terminal-Bench ScienceVals AI1.4%–
Time Horizon Index: KSPVals AI10.5%–
PostTrainBenchEpoch AI Benchmarking Hub31.5%†–
GBAEvalEpoch AI Benchmarking Hub48.4%†–
Vending-Bench 2Andon Labs5165.0†–
AutomationBenchArtificial Analysis58.3%40.6%
GDP.pdf (AA)Artificial Analysis22.0%17.4%
Harvey LAB-AA v1.1Harvey5.3%–
EnterpriseOps-GymArtificial Analysis45.3%47.3%
AA-Briefcase v1.1Artificial Analysis14971324
GDPxGDPx by SemiAnalysis3.7%–
Design Arena AgenticDesign Arena1255†1179†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis8.1%–
CWE-Bench (AA)Artificial Analysis53.3%–
DeepSec-Bench (AA)Artificial Analysis12.4%–
CyberGym end-to-end (AA)Artificial Analysis58.0%–
FACTS SearchGoogle90.3%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub72.2%–
FrontierMath Tier 4Epoch AI Benchmarking Hub39.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub97.2%–
ProofBenchVals AI87.0%†43.0%†
LiveBench MathematicsLiveBench84.4%†91.2%
AIME 2026MathArena96.7%–
HMMT February 2026MathArena97.0%–
MathArena ApexMathArena65.6%–
Arena MathsArena (LMArena)15031490
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub50.6%60.3%
LiveBench 2.0 Data AnalysisLiveBench78.7%†–
LiveBench ResearchLiveBench79.8%†–
LiveBench 1.0 Data AnalysisLiveBench78.7%†76.5%
AA-Omniscience v1.1Artificial Analysis-1.7†–
MMLU-ProVals AI88.0%88.3%
LegalBenchVals AI86.2%85.3%
CorpFinVals AI71.6%†70.9%
TaxEvalVals AI75.7%†80.4%
BioMysteryBenchVals AI72.6%64.8%
Excel Modeling BenchmarkVals AI66.7%57.0%
Excel Modeling Benchmark v1.1Vals AI71.3%–
MedCodeVals AI49.4%49.4%
MedScribeVals AI88.0%90.1%
Public Benefits Bench v1.1Vals AI68.2%68.5%
GDP.pdfEpoch AI Benchmarking Hub19.0%16.0%
AA-Omniscience v1.1: accuracyArtificial Analysis42.4%†–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis23.4%†–
HealthBench Professional (AA)OpenAI53.2%–
Instruction following
LiveBench LanguageLiveBench85.5%†78.6%
LiveBench Instruction FollowingLiveBench71.4%†74.3%
Arena Instruction FollowingArena (LMArena)14881479
Human preference
Arena TextArena (LMArena)14871494
EQ-Bench 4EQ-Bench1319†–
Arena Creative WritingArena (LMArena)14591443
Arena Multi-turnArena (LMArena)15011512
Arena Longer QueriesArena (LMArena)15001491
Multimodal
Arena VisionArena (LMArena)–1305
LiveBench DesignLiveBench72.5%†–
MMMU-ProArtificial Analysis80.5%–
MMMU-Pro (Vals)Vals AI88.2%†86.1%
MortgageTaxVals AI66.3%†65.4%
SAGEVals AI86.8%–
Blueprint-Bench 2Epoch AI Benchmarking Hub29.5%†–
Code2Video-AAArtificial Analysis1041–
AA-3DArtificial Analysis984–
Long context
AA-LCR v1.1Artificial Analysis88.7%79.0%
MLCRArtificial Analysis21.7%7.2%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub158.6†155.0†
LiveBench 2.0LiveBench65.0%†–
LiveBench 1.0LiveBench79.2%†78.0%
AA Intelligence Index v5.0Artificial Analysis17.4†–
AA Intelligence Index v4.3.2Artificial Analysis43.639.6
AA Progress Index v1Artificial Analysis319.9309.1
Vals IndexVals AI53.0–
Vals Finance IndexVals AI58.0%–
Vals RSI IndexVals AI20.9%–
Vals Multimodal IndexVals AI73.4%†69.8%†
Vals Router IndexVals AI53.0%†–
AA Cyber IndexArtificial Analysis41.3–
Safety & honesty
FORTRESSScale AI SEAL26.6%–
Metadata
AA Openness IndexArtificial Analysis38.9–

Data as of 2026-11-12. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), 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 (max): 3 new results (AIME 2026, HMMT February 2026, MathArena Apex).
  • Kimi K3 (max): 1 new result (MirrorCode); 1 score revision.
  • Kimi K3 (max): 1 score revision.
  • Kimi K3 (max): 2 score revisions.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • Kimi K3 (max): 1 new result (MirrorCode).
  • Kimi K3 (max): 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • Kimi K3 (max): BenchLeader Index 63.1 → 62.1.
  • Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.

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

Kimi K3 vs Muse Spark 1.2: questions

Is Kimi K3 better than Muse Spark 1.2?
Kimi K3 (max) and Muse Spark 1.2 (xhigh) are neck and neck on quality (62.0 vs 61.6, within the ±5.9 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 12 Nov 2026, so check the category scores for your use.
Kimi K3 vs Muse Spark 1.2: which is cheaper, and will that change?
Muse Spark 1.2 is cheaper today: $2.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Kimi K3 or Muse Spark 1.2 better for coding?
Kimi K3 scores higher in coding (64 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1658 for Kimi K3 against 1534 for Muse Spark 1.2.
Which is faster, Kimi K3 or Muse Spark 1.2?
Muse Spark 1.2 streams 3×+ faster (204 vs 46 output tokens per second, Artificial Analysis 7-day median).
Is Kimi K3 or Muse Spark 1.2 better for agents and tool use?
Kimi K3 scores higher in agentic tasks (58 vs 56 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 46.0% for Kimi K3 against 34.9% for Muse Spark 1.2.
More questions (4)
Which is better for long documents?
Kimi K3 scores higher on long-context benchmarks (69 vs 64). Both accept 1,048,576 tokens of context.
Which has lower latency?
Muse Spark 1.2 answers first: 7.9 s against 78.8 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 vs Muse Spark 1.2?
Across the 48 benchmarks both have, Kimi K3 leads 36, Muse Spark 1.2 leads 12. Every overall index that rates both puts Muse Spark 1.2 ahead.
When was Muse Spark 1.2 released?
Muse Spark 1.2 was released on 5 Aug 2026.