BenchLeader

MiMo-V2.6-Pro vs Muse Spark 1.2

Full profiles: MiMo-V2.6-Pro (Xiaomi) and Muse Spark 1.2 (Meta): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, MiMo-V2.6-Pro and Muse Spark 1.2 are neck and neck on quality (57.5 vs 61.5 on the BenchLeader Index, inside the ±6.4 margin), and MiMo-V2.6-Pro is 3.7× cheaper at $0.544 vs $2.00 per 1M tokens blended. Choose MiMo-V2.6-Pro for coding (59 vs 55), long context (68 vs 64), and agents & tools (57 vs 55); choose Muse Spark 1.2 for fast first answers (11.4 s vs 42.3 s) and knowledge (65 vs 42), reasoning (68 vs 50), and multimodal (65 vs 60), where it also streams 3×+ faster.

Key facts (as of 16 Nov 2026)

  • MiMo-V2.6-Pro scores 57.5 on the BenchLeader Index and Muse Spark 1.2 scores 61.5 (BenchLeader, 16 Nov 2026).
  • MiMo-V2.6-Pro costs $0.544 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Spark 1.2 streams 3×+ faster than MiMo-V2.6-Pro (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 41 benchmarks both models have, MiMo-V2.6-Pro leads 27 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, MiMo-V2.6-Pro is rated 1625 and Muse Spark 1.2 1534 (LMArena, as published by 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
CodingMiMo-V2.6-Pro59 vs 55 category score; Arena WebDev 1625 vs 1534Medium
Agents & tool useMiMo-V2.6-Pro57 vs 55 category score; Arena Agent 2.4 vs -8.2Medium
MathsMuse Spark 1.267 vs 66 category score; Arena Maths 1486 vs 1484Medium
ReasoningMuse Spark 1.268 vs 50 category score; Arena Hard Prompts 1514 vs 1504High
KnowledgeMuse Spark 1.265 vs 42 category score; MedCode 49.4% vs 45.0%High
Long documentsMiMo-V2.6-Pro68 vs 64 category score; AA-LCR v1.1 86.3% vs 79.0%Medium
Images and other mediaMuse Spark 1.265 vs 60 category score; Arena Vision 1305 vs 1266Medium
Chat quality (human preference)Muse Spark 1.269 vs 67 on Arena votesMedium
Lowest costMiMo-V2.6-Pro$0.548 vs $2.00 per 1M blended; agentic coding session $0.030 vs $0.092–
Fastest first answerMuse Spark 1.211.4 s (Muse Spark 1.2 (xhigh)) vs 42.3 s (MiMo-V2.6-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

  • MiMo-V2.6-Pro and Muse Spark 1.2 (xhigh) are neck and neck on quality (57.5 vs 61.5, within the ±6.4 margin).
  • MiMo-V2.6-Pro is stronger in agents & tools, coding, long context.
  • Muse Spark 1.2 (xhigh) is stronger in human preference, knowledge, maths, multimodal, reasoning.
  • MiMo-V2.6-Pro is 3.7× cheaper ($0.544 vs $2.00 per 1M blended).
  • Muse Spark 1.2 (xhigh) streams 3.9× faster (208 vs 54 tokens per second).

At a glance

SpecMiMo-V2.6-ProMuse Spark 1.2
DeveloperXiaomiMeta
Released21 Sep 20265 Aug 2026
Context window (tokens)1,048,5761,048,576
Compared atMiMo-V2.6-ProMuse Spark 1.2 (xhigh)
Open weightsYesNo
Price in / out / cached input per 1M$0.440 / $0.870 / $0.0036$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.

CategoryMiMo-V2.6-ProMuse Spark 1.2 (xhigh)Leader
Reasoning49.968.1Muse Spark 1.2
Coding58.854.7MiMo-V2.6-Pro
Agents & tools57.155.4MiMo-V2.6-Pro
Maths65.566.8Muse Spark 1.2
Knowledge42.364.5Muse Spark 1.2
Human preference67.068.6Muse Spark 1.2
Multimodal60.265.3Muse Spark 1.2
Long context67.964.1MiMo-V2.6-Pro

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 contextMultimodalHumanpreferenceMiMo-V2.6-Pro, Reasoning: 49.9MiMo-V2.6-Pro, Coding: 58.8MiMo-V2.6-Pro, Agents & tools: 57.1MiMo-V2.6-Pro, Maths: 65.5MiMo-V2.6-Pro, Knowledge: 42.3MiMo-V2.6-Pro, Long context: 67.9MiMo-V2.6-Pro, Multimodal: 60.2MiMo-V2.6-Pro, Human preference: 67.0Muse Spark 1.2, Reasoning: 68.1Muse Spark 1.2, Coding: 54.7Muse Spark 1.2, Agents & tools: 55.4Muse Spark 1.2, Maths: 66.8Muse Spark 1.2, Knowledge: 64.5Muse Spark 1.2, Long context: 64.1Muse Spark 1.2, Multimodal: 65.3Muse Spark 1.2, Human preference: 68.6

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

Model, click to add or removeIndex

Where sources disagree

Across the 41 benchmarks both have, MiMo-V2.6-Pro leads 27, Muse Spark 1.2 leads 13 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.2 ahead.

Overall indexMiMo-V2.6-ProMuse Spark 1.2 (xhigh)Leader
BenchLeader Index57.561.5neck and neck
Arena Text14801493Muse 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.

MeasureMiMo-V2.6-ProMuse Spark 1.2 (xhigh)
Blended price per 1M tokens$0.548$2.00
Input / output per 1M$0.440 / $0.870$1.25 / $4.25
Cached input per 1M$0.0036$0.150
Price per task: chat reply$0.0004$0.0018
Price per task: summarize a 30-page report$0.0058$0.018
Price per task: code edit$0.0039$0.014
Price per task: agentic coding session$0.030$0.092
Price per task: structured extraction$0.0011$0.0034
Agentic coding session, input mostly cached$0.010$0.043
Cost per benchmark task (AA Index)$0.257–
Output tokens per task (AA Index)121k–
Of which reasoning86k–
Time per task (AA Index)38 min–
Output speed54 tok/s208 tok/s
Time to first answer42.3 s11.4 s
Time to a complete answer, last measured 13 Nov 202695.7 s23.9 s

Each model is compared at its best-ranked reasoning-effort setting. MiMo-V2.6-Pro scores 57.5 and takes 42 s to its first answer token. Muse Spark 1.2 (xhigh) scores 61.5 and takes 11 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

129 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.

MetricPublisherMiMo-V2.6-ProMuse Spark 1.2 (xhigh)
BenchLeader IndexBenchLeader57.561.5
Agents & tools scoreBenchLeader57.155.4
Coding scoreBenchLeader58.854.7
Human preference scoreBenchLeader67.068.6
Knowledge scoreBenchLeader42.364.5
Long context scoreBenchLeader67.964.1
Maths scoreBenchLeader65.566.8
Multimodal scoreBenchLeader60.265.3
Reasoning scoreBenchLeader49.968.1
Blended price $/MBenchLeader$0.548$2.00
Output speedBenchLeader54 tok/s208 tok/s
Time to first answerBenchLeader42.3 s11.4 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
SimpleBenchSimpleBench–74.5%†
Arena Hard PromptsArena (LMArena)15041514
LiveBench 2.0 ReasoningLiveBench79.6%†–
LiveBench 1.0 ReasoningLiveBench–90.0%
GPQA Diamond (AA)Artificial Analysis–90.4%
Humanity's Last Exam (AA)Artificial Analysis49.4%45.5%
HLE-Diamond (AA)Artificial Analysis15.2%–
CritPtArtificial Analysis26.6%17.7%
CritPt v2 hard subset (AA)Artificial Analysis34.0%–
MysteryMechanismVals AI15.3%–
Arena ExpertArena (LMArena)15261503
Chess PuzzlesEpoch AI Benchmarking Hub–27.0%
LMCAEpoch AI Benchmarking Hub–48.4%
DTBenchEpoch AI Benchmarking Hub–94.7%
Coding
SciCodeSciCode60.9%57.4%
WeirdMLWeirdML–60.3%
Arena CodingArena (LMArena)15381542
Arena WebDevArena (LMArena)16251534
LiveBench 2.0 CodingLiveBench64.5%†–
LiveBench 1.0 CodingLiveBench–77.5%
IOIVals AI39.3%21.8%
SWE-bench (Vals)Vals AI–86.6%
Code MigrationVals AI43.0%29.9%
Code Migration v1.1Vals AI48.8%–
ProgramBenchVals AI0.5%0.5%
Show all 129 benchmarks
MetricPublisherMiMo-V2.6-ProMuse Spark 1.2 (xhigh)
Coding
SWE-bench MultimodalVals AI41.3%–
Vibe Code Bench v1.1Vals AI85.2%79.1%
Vibe Code Bench 1-100 v1.1Vals AI26.4%–
DeepSWE v1.1Epoch AI Benchmarking Hub–54.9%
ALE-BenchEpoch AI Benchmarking Hub1158.1–
FrontierSWEEpoch AI Benchmarking Hub–12.0%
Terminal-Bench 4.0 (AA)Artificial Analysis34.9%7.1%
Terminal-Bench 2.1 (AA)Artificial Analysis–80.2%
Startrise FrontendStartrise–70.3%†
GameBench 2 OverallDuelLab GameBench 2–51.5†
GameBench 2 by reasoning settingDuelLab GameBench 249.8†56.9
Design Arena WebsiteDesign Arena13111309†
FrontierCode 1.1 (AA)Artificial Analysis45.4%–
FrontierCode 2.0 (AA)Artificial Analysis24.0%–
Agents & tools
Terminal-BenchTerminal-Bench27.0%†–
APEX-AgentsMercor54.4%45.4%†
Arena AgentArena (LMArena)2.4-8.2
LiveBench Long AgenticLiveBench36.4%†–
LiveBench BrowserLiveBench77.3%†–
LiveBench Agentic CodingLiveBench–57.6%
Terminal-Bench 2.1 (Vals)Vals AI67.8%69.7%
GDPval-AA v2.1, normalised scoreArtificial Analysis59.1%–
GDPval-AA v2.1Artificial Analysis16921478
τ³-Banking (AA)Artificial Analysis–34.9%
Analyst Agent (AA)Artificial Analysis37.5%–
CyberBenchVals AI72.9%69.5%
Finance Agent v2Vals AI57.3%60.6%
Finance Agent v2.1Vals AI64.3%–
Harvey's Legal Agent Benchmark v1.1Vals AI13.8%–
Harvey's Legal Agent Benchmark v1Vals AI10.8%25.4%
Legal Research BenchVals AI47.1%43.8%
SkillsBenchVals AI–53.0%
SREBenchVals AI3.0%0.0%
Tax Agent BenchVals AI32.4%32.8%
Terminal-Bench 4.0 (Vals)Vals AI31.3%6.1%
Terminal-Bench ScienceVals AI2.9%–
Arena Agent Task CompletionArena (LMArena)5-9.8
AutomationBenchArtificial Analysis58.6%40.6%
GDP.pdf (AA)Artificial Analysis19.2%17.4%
EnterpriseOps-GymArtificial Analysis–47.3%
AA-Briefcase v1.1Artificial Analysis15121323
Design Arena AgenticDesign Arena12711185†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis5.7%–
CWE-Bench (AA)Artificial Analysis63.3%–
DeepSec-Bench (AA)Artificial Analysis26.2%–
CyberGym end-to-end (AA)Artificial Analysis78.6%–
MKA (AA)Artificial Analysis37.3%–
Maths
ProofBenchVals AI70.0%43.0%†
LiveBench MathematicsLiveBench–91.2%
Arena MathsArena (LMArena)14841486
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–60.3%
LiveBench 2.0 Data AnalysisLiveBench72.3%†–
LiveBench ResearchLiveBench84.8%†–
LiveBench 1.0 Data AnalysisLiveBench–76.5%
AA-Omniscience v1.1Artificial Analysis-4.5–
MMLU-ProVals AI–88.3%
LegalBenchVals AI–85.3%
CorpFinVals AI–70.9%
TaxEvalVals AI–80.4%
BioMysteryBenchVals AI–64.8%
Excel Modeling BenchmarkVals AI62.9%57.0%
Excel Modeling Benchmark v1.1Vals AI67.3%–
MedCodeVals AI45.0%49.4%
MedScribeVals AI88.3%90.1%
Public Benefits Bench v1.1Vals AI68.9%68.5%
Access to Justice BenchmarkVals AI70.0%–
Financial Coaching BenchVals AI75.4%75.7%
Immigration BenchVals AI67.5%66.5%
GDP.pdfEpoch AI Benchmarking Hub–16.0%
AA-Omniscience v1.1: accuracyArtificial Analysis34.8%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis39.8%–
Instruction following
LiveBench LanguageLiveBench–78.6%
LiveBench Instruction FollowingLiveBench–74.3%
Arena Instruction FollowingArena (LMArena)14721479
Human preference
Arena TextArena (LMArena)14801493
EQ-Bench Creative Writing v3EQ-Bench–1842†
Arena Creative WritingArena (LMArena)14481443
Arena Multi-turnArena (LMArena)14621510
Arena Longer QueriesArena (LMArena)14961491
Multimodal
Arena VisionArena (LMArena)12661305
LiveBench DesignLiveBench74.3%†–
MMMU-Pro (Vals)Vals AI–86.1%
MortgageTaxVals AI–65.4%
SAGEVals AI84.5%–
Humanity's Sixth SenseScale AI SEAL25.2%†24.5%
VIALS-AAHandshake AI43.5%–
Code2Video-AAArtificial Analysis1052–
AA-3DArtificial Analysis983–
Long context
AA-LCR v1.1Artificial Analysis86.3%79.0%
MLCRArtificial Analysis12.8%7.2%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–155.0†
LiveBench 2.0LiveBench66.1%†–
LiveBench 1.0LiveBench–78.0%
AA Intelligence Index v5.0.1Artificial Analysis29.9–
AA Intelligence Index v4.3.2Artificial Analysis46.339.6
AA Progress Index v1Artificial Analysis321.2309.1
Vals IndexVals AI57.8–
Vals Finance IndexVals AI57.9%–
Vals Multimodal IndexVals AI–69.8%†
Vals Router IndexVals AI57.8%–
Vals Legal IndexVals AI72.1%–
AA Cyber IndexArtificial Analysis56.1–
Safety & honesty
DistressBenchScale AI SEAL–88.4%†
Metadata
AA Openness IndexArtificial Analysis52.8–

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

  • MiMo-V2.6-Pro: 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 new result (GDPval-AA v2.1).
  • MiMo-V2.6-Pro: 1 score revision.
  • MiMo-V2.6-Pro: 6 score revisions.
  • MiMo-V2.6-Pro: 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • MiMo-V2.6-Pro: 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • MiMo-V2.6-Pro: BenchLeader Index 61.1 → 57.2.
  • Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.

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

MiMo-V2.6-Pro vs Muse Spark 1.2: questions

Is MiMo-V2.6-Pro better than Muse Spark 1.2?
MiMo-V2.6-Pro and Muse Spark 1.2 (xhigh) are neck and neck on quality (57.5 vs 61.5, within the ±6.4 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.
MiMo-V2.6-Pro vs Muse Spark 1.2: which is cheaper, and will that change?
MiMo-V2.6-Pro is cheaper today: $0.544 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is MiMo-V2.6-Pro or Muse Spark 1.2 better for coding?
MiMo-V2.6-Pro scores higher in coding (59 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1625 for MiMo-V2.6-Pro against 1534 for Muse Spark 1.2.
Which is faster, MiMo-V2.6-Pro or Muse Spark 1.2?
Muse Spark 1.2 streams 3×+ faster (208 vs 54 output tokens per second, Artificial Analysis 7-day median).
Is MiMo-V2.6-Pro or Muse Spark 1.2 better for agents and tool use?
MiMo-V2.6-Pro scores higher in agentic tasks (57 vs 55 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 2.4 for MiMo-V2.6-Pro against -8.2 for Muse Spark 1.2.
More questions (4)
Which is better for long documents?
MiMo-V2.6-Pro scores higher on long-context benchmarks (68 vs 64). Both accept 1,048,576 tokens of context.
Which has lower latency?
Muse Spark 1.2 answers first: 11.4 s against 42.3 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 MiMo-V2.6-Pro vs Muse Spark 1.2?
Across the 41 benchmarks both have, MiMo-V2.6-Pro leads 27, Muse Spark 1.2 leads 13 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.2 ahead.
When was MiMo-V2.6-Pro released?
MiMo-V2.6-Pro was released on 21 Sep 2026.