BenchLeader

MiMo-V2.5-Pro vs Muse Spark 1.3

Full profiles: MiMo-V2.5-Pro (Xiaomi) 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 MiMo-V2.5-Pro on quality (61.6 vs 55.5 on the BenchLeader Index), but MiMo-V2.5-Pro is 1.3× cheaper at $1.50 vs $2.00 per 1M tokens blended. Choose MiMo-V2.5-Pro for maths (58 vs 56); choose Muse Spark 1.3 for knowledge (81 vs 55), agents & tools (61 vs 46), and reasoning (71 vs 66), where it also streams ~2× faster.

Key facts (as of 16 Nov 2026)

  • MiMo-V2.5-Pro scores 55.5 on the BenchLeader Index and Muse Spark 1.3 scores 61.6 (BenchLeader, 16 Nov 2026).
  • MiMo-V2.5-Pro costs $1.50 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 ~2× faster than MiMo-V2.5-Pro (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 4 benchmarks both models have, Muse Spark 1.3 leads 4 (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 46 category scoreHigh
MathsMiMo-V2.5-Pro58 vs 56 category score; ProofBench 22.0% vs 55.0%Medium
ReasoningMuse Spark 1.371 vs 66 category score; LMCA 53.9% vs 29.5%Medium
KnowledgeMuse Spark 1.381 vs 55 category scoreHigh
Chat quality (human preference)–Only MiMo-V2.5-Pro has an Arena rating (60 category score)Not comparable
Lowest costMiMo-V2.5-Pro$1.50 vs $2.00 per 1M blended; agentic coding session $0.072 vs $0.092–
Fastest first answerEither2.8 s (MiMo-V2.5-Pro) 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

  • Muse Spark 1.3 leads on quality: 61.6 vs 55.5.
  • MiMo-V2.5-Pro is stronger in maths.
  • Muse Spark 1.3 is stronger in agents & tools, knowledge, reasoning.
  • MiMo-V2.5-Pro is 1.3× cheaper ($1.50 vs $2.00 per 1M blended).
  • Muse Spark 1.3 streams 2.4× faster (163 vs 68 tokens per second).

At a glance

SpecMiMo-V2.5-ProMuse Spark 1.3
DeveloperXiaomiMeta
Released23 Apr 20262 Sep 2026
Context window (tokens)1,048,5761,048,576
Compared atMiMo-V2.5-ProMuse Spark 1.3
Open weightsYesNo
Price in / out / cached input per 1M$1.00 / $3.00 / $0.0043$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-V2.5-ProMuse Spark 1.3Leader
Reasoning65.871.0Muse Spark 1.3
Coding56.2–not comparable
Agents & tools46.061.3Muse Spark 1.3
Maths57.656.3MiMo-V2.5-Pro
Knowledge54.581.2Muse Spark 1.3
Human preference60.1–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 & toolsMathsKnowledgeMiMo-V2.5-Pro, Reasoning: 65.8MiMo-V2.5-Pro, Agents & tools: 46.0MiMo-V2.5-Pro, Maths: 57.6MiMo-V2.5-Pro, Knowledge: 54.5Muse 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 4 benchmarks both have, MiMo-V2.5-Pro leads 0, Muse Spark 1.3 leads 4. Every overall index that rates both puts Muse Spark 1.3 ahead.

Overall indexMiMo-V2.5-ProMuse Spark 1.3Leader
BenchLeader Index55.561.6Muse Spark 1.3
Arena Text14661497†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.

MeasureMiMo-V2.5-ProMuse Spark 1.3
Blended price per 1M tokens$1.50$2.00
Input / output per 1M$1.00 / $3.00$1.25 / $4.25
Cached input per 1M$0.0043$0.150
Price per task: chat reply$0.0013$0.0018
Price per task: summarize a 30-page report$0.014$0.018
Price per task: code edit$0.011$0.014
Price per task: agentic coding session$0.072$0.092
Price per task: structured extraction$0.0026$0.0034
Agentic coding session, input mostly cached$0.027$0.043
Output speed68 tok/s163 tok/s
Time to first answer2.8 s2.6 s

Each model is compared at its best-ranked reasoning-effort setting. MiMo-V2.5-Pro scores 55.5 and takes 3 s to its first answer token. 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

136 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-V2.5-ProMuse Spark 1.3
BenchLeader IndexBenchLeader55.561.6
Agents & tools scoreBenchLeader46.061.3
Coding scoreBenchLeader56.2–
Human preference scoreBenchLeader60.1–
Knowledge scoreBenchLeader54.581.2
Maths scoreBenchLeader57.656.3
Reasoning scoreBenchLeader65.871.0
Blended price $/MBenchLeader$1.50$2.00
Output speedBenchLeader68 tok/s163 tok/s
Time to first answerBenchLeader2.8 s2.6 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
SimpleBenchSimpleBench–81.8%
Arena Hard PromptsArena (LMArena)14941517†
LiveBench 2.0 ReasoningLiveBench–89.7%†
LiveBench 1.0 ReasoningLiveBench–89.7%†
GPQA Diamond (AA)Artificial Analysis76.2%†93.5%†
Humanity's Last Exam (AA)Artificial Analysis14.8%†48.7%†
HLE-Diamond (AA)Artificial Analysis–33.7%†
GPQA Diamond (Vals)Vals AI82.6%–
CritPtArtificial Analysis1.1%†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)15071521†
Chess PuzzlesEpoch AI Benchmarking Hub–37.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub–25.0%†
LMCAEpoch AI Benchmarking Hub29.5%53.9%
DTBenchEpoch AI Benchmarking Hub84.5%96.5%
ForecastBenchForecastBench–65.5%†
BTF-3Epoch AI Benchmarking Hub–14.1%†
Coding
SciCodeSciCode50.2%58.8%†
Arena CodingArena (LMArena)15201534†
Arena WebDevArena (LMArena)14791655†
LiveBench 2.0 CodingLiveBench–84.4%†
LiveBench 1.0 CodingLiveBench–81.1%†
SciCode (AA)Artificial Analysis50.6%†58.8%†
Show all 136 benchmarks
MetricPublisherMiMo-V2.5-ProMuse Spark 1.3
Coding
LiveCodeBenchVals AI81.3%–
IOIVals AI–56.6%†
SWE-bench (Vals)Vals AI74.0%–
Code MigrationVals AI21.6%47.4%†
ProgramBenchVals AI–2.5%†
SWE-bench MultimodalVals AI–43.1%†
Vibe Code Bench 1-100Vals AI–20.5%†
Vibe Code Bench v1.1Vals AI34.1%85.9%†
MirrorCodeEpoch AI Benchmarking Hub–54.4%†
CursorBenchCursor–41.6%†
ALE-BenchEpoch AI Benchmarking Hub899.81688.3†
FrontierSWEEpoch AI Benchmarking Hub–25.8%†
WeirdML v3WeirdML–6.7%†
Terminal-Bench 4.0 (AA)Artificial Analysis0.0%†33.3%†
Terminal-Bench 2.1 (AA)Artificial Analysis65.2%†84.3%†
Startrise FrontendStartrise–74.7%
GameBench 2 OverallDuelLab GameBench 2–57.7
GameBench 2 by reasoning settingDuelLab GameBench 227.4†68.5†
Design Arena WebsiteDesign Arena12621353†
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 CodingLiveBench–64.1%†
Terminal-Bench HardArtificial Analysis35.6%†–
τ²-Bench Telecom (AA)Artificial Analysis72.5%†–
Terminal-Bench 2.1 (Vals)Vals AI57.3%79.0%†
HiL-BenchScale AI SEAL–66.9%
GDPval-AA v2.1Artificial Analysis1128†1681†
τ³-Banking (AA)Artificial Analysis9.9%†50.5%†
ITBench SRE (AA)Artificial Analysis38.2%†33.2%†
Analyst Agent (AA)Artificial Analysis20.0%†37.5%†
APEX-Agents (AA)Artificial Analysis2.4%†–
CUA-benchVals AI–5.8%†
CyberBenchVals AI–72.7%†
Finance Agent v2Vals AI41.5%60.0%†
Harvey's Legal Agent Benchmark v1Vals AI2.1%23.8%†
Legal Research BenchVals AI15.9%55.3%†
SREBenchVals AI–3.8%†
Tax Agent BenchVals AI11.5%42.4%†
Terminal-Bench 4.0 (Vals)Vals AI0.5%24.8%†
Terminal-Bench ScienceVals AI–10.0%†
Arena Agent Task CompletionArena (LMArena)–3.7†
AutomationBenchArtificial Analysis13.7%†57.9%†
GDP.pdf (AA)Artificial Analysis4.0%†26.6%†
Harvey LAB-AA v1.1Harvey–8.9%†
AA-Briefcase v1.1Artificial Analysis884†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 Hub–74.0%†
FrontierMath Tier 4Epoch AI Benchmarking Hub–46.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub–99.2%†
ProofBenchVals AI22.0%55.0%
LiveBench MathematicsLiveBench–96.0%†
Arena MathsArena (LMArena)14791506†
Knowledge
LiveBench 2.0 Data AnalysisLiveBench–79.6%†
LiveBench ResearchLiveBench–82.5%†
LiveBench 1.0 Data AnalysisLiveBench–79.6%†
AA-Omniscience v1.1Artificial Analysis–22.4†
MMLU-ProVals AI84.6%–
LegalBenchVals AI77.1%–
CorpFinVals AI61.4%–
TaxEvalVals AI73.8%–
PRBench FinanceScale AI SEAL–59.5%
PRBench LegalScale AI SEAL–61.6%
Excel Modeling BenchmarkVals AI55.2%67.4%†
MedCodeVals AI32.5%–
MedScribeVals AI83.7%–
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 LanguageLiveBench–82.8%†
LiveBench Instruction FollowingLiveBench–78.0%†
IFBenchArtificial Analysis42.7%†–
Arena Instruction FollowingArena (LMArena)14681485†
Human preference
Arena TextArena (LMArena)14661497†
EQ-Bench 4EQ-Bench1198–
EQ-Bench Creative Writing v3EQ-Bench14931907
Arena Creative WritingArena (LMArena)14331468†
Arena Multi-turnArena (LMArena)14801493†
Arena Longer QueriesArena (LMArena)14861498†
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 Analysis41.7%†83.0%†
Arena DocumentArena (LMArena)–1474†
MLCRArtificial Analysis5.6%†13.9%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–158.2
LiveBench 2.0LiveBench–68.6%†
LiveBench 1.0LiveBench–81.6%†
AA Intelligence Index v5.0.1Artificial Analysis–36.6†
AA Intelligence Index v4.3.2Artificial Analysis18.3†48.1†
AA Progress Index v1Artificial Analysis241†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 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

  • Muse Spark 1.3: BenchLeader Index 60.2 → 61.6.
  • MiMo-V2.5-Pro: MiMo-V2.5-Pro cached input price moved from $0.20/M to $0.0043/M (98% down).
  • 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).
  • MiMo-V2.5-Pro: BenchLeader Index 55.0 → 55.6.
  • 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.

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

MiMo-V2.5-Pro vs Muse Spark 1.3: questions

Is Muse Spark 1.3 better than MiMo-V2.5-Pro?
Muse Spark 1.3 leads on quality: 61.6 vs 55.5. 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.
MiMo-V2.5-Pro vs Muse Spark 1.3: which is cheaper, and will that change?
MiMo-V2.5-Pro is cheaper today: $1.50 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, MiMo-V2.5-Pro or Muse Spark 1.3?
Muse Spark 1.3 streams ~2× faster (163 vs 68 output tokens per second, Artificial Analysis 7-day median).
Is MiMo-V2.5-Pro or Muse Spark 1.3 better for agents and tool use?
Muse Spark 1.3 scores higher in agentic tasks (61 vs 46 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 2.8 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 MiMo-V2.5-Pro vs Muse Spark 1.3?
Across the 4 benchmarks both have, MiMo-V2.5-Pro leads 0, Muse Spark 1.3 leads 4. Every overall index that rates both puts Muse Spark 1.3 ahead.
When was Muse Spark 1.3 released?
Muse Spark 1.3 was released on 2 Sep 2026.