Skip to main content

Model comparison

MiMo-V2.5 vs Muse Spark

Data verified

Head-to-head evidence from 5 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Xiaomi
58.62/100
Margin
12.4pts
winning →
71.04/100
1 category wins2 category wins

Public leaderboard positions: MiMo-V2.5 #62 (Estimated); Muse Spark #13 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiMo-V2.5 and Muse Spark share 5 comparable benchmark results. 3 of 8 categories are comparable. 6 results are unique to MiMo-V2.5; 34 to Muse Spark.

Updated July 21, 2026
Shared results
5
MiMo-V2.5 only
6
Muse Spark only
34
Comparable categories
3 / 8

Pick Muse Spark if you want the stronger benchmark profile. MiMo-V2.5 only becomes the better choice if agentic is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 3 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Muse Spark is clearly ahead on the BenchAlign aggregate, 71.04 to 58.62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Muse Spark's sharpest advantage is in coding, where it averages 67.8 against 56.1. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 65.8% to 59%. MiMo-V2.5 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

MiMo-V2.5 gives you the larger context window at 1M, compared with 262K for Muse Spark.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for MiMo-V2.5 and Muse Spark
CategoryMiMo-V2.5ΔMuse Spark
CodingMiMo-V2.556.1Margin 11.7Muse Spark67.8
AgenticMiMo-V2.565.8Margin 6.8Muse Spark59.0
MultimodalMiMo-V2.579.0Margin 3.5Muse Spark82.5
ReasoningMiMo-V2.5Not measuredMarginNo overlapMuse Spark42.5
KnowledgeMiMo-V2.5Not measuredMarginNo overlapMuse Spark50.4
MathMiMo-V2.5Not measuredMarginNo overlapMuse Spark32.9

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · MiMo-V2.5B · Muse Spark
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 65.8%B 59%
    Winner: MiMo-V2.5Δ 6.8
    Terminal-Bench 2.0: MiMo-V2.5 scored 65.8%; Muse Spark scored 59%. MiMo-V2.5 wins this benchmark.
  2. CharXiv

    Multimodal
    Source ↗
    A 81%B 86.4%
    Winner: Muse SparkΔ 5.4
    CharXiv: MiMo-V2.5 scored 81%; Muse Spark scored 86.4%. Muse Spark wins this benchmark.
  3. SWE-bench Pro

    Coding
    Source ↗
    A 56.1%B 52.4%
    Winner: MiMo-V2.5Δ 3.7
    SWE-bench Pro: MiMo-V2.5 scored 56.1%; Muse Spark scored 52.4%. MiMo-V2.5 wins this benchmark.
  4. MMMU-Pro

    Multimodal
    Source ↗
    A 77.9%B 80.4%
    Winner: Muse SparkΔ 2.5
    MMMU-Pro: MiMo-V2.5 scored 77.9%; Muse Spark scored 80.4%. Muse Spark wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricMiMo-V2.5Muse SparkComparison
Input / output priceUSD per 1M tokensMiMo-V2.5Not availableMuse SparkNot availableA complete price comparison is not available.
Generation speedtokens per secondMiMo-V2.5Not availableMuse SparkNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiMo-V2.5Not availableMuse SparkNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiMo-V2.51MMuse Spark262KMiMo-V2.5 lists the larger context window.

Benchmark Deep Dive

AgenticMiMo-V2.5 wins
BenchmarkMiMo-V2.5Muse SparkResult
Claw-EvalSource 62.3%63.8%Muse Spark leads
MM-ClawBenchSource 23.8%Not comparable
Terminal-Bench 2.0Source 65.8%59%MiMo-V2.5 leads
Gert LabsSource 46.89%Not comparable
ResearchClawBenchSource 16.9%Not comparable
τ²-bench resultsSource 91.5%Not comparable
DeepSearchQASource 74.8%Not comparable
CyberGymSource 43.5%Not comparable
AA Agentic IndexSource 28.7%Not comparable
GDPval-AASource 32.2%Not comparable
GDPval-AASource 1144Not comparable
CodingMuse Spark wins
BenchmarkMiMo-V2.5Muse SparkResult
SWE-bench ProSource 56.1%52.4%MiMo-V2.5 leads
Terminal-Bench 2.0Source 65.8%Not comparable
SWE-bench VerifiedSource 77.4%Not comparable
LiveCodeBench ProSource 80.0%Not comparable
Vibe Code BenchSource 19.67%Not comparable
AA Coding IndexSource 58.6%Not comparable
AA-SciCodeSource 51.5%Not comparable
Reasoning
BenchmarkMiMo-V2.5Muse SparkResult
ARC-AGI-2Source 42.5%Not comparable
AA-LCRSource 69.7%Not comparable
CritPtSource 11.3%Not comparable
Knowledge
BenchmarkMiMo-V2.5Muse SparkResult
GPQA-DSource 89.5%Not comparable
HLESource 50.4%Not comparable
HLE w/o toolsSource 42.8%Not comparable
HealthBench HardSource 42.8%Not comparable
MedXpertQA (Text)Source 52.6%Not comparable
Artificial Analysis Intelligence IndexSource 43.1%Not comparable
AA-GPQA DiamondSource 88.4%Not comparable
AA-HLESource 39.9%Not comparable
AA-Omniscience IndexSource 4.1%Not comparable
AA-Omniscience AccuracySource 44.6%Not comparable
AA-Omniscience Hallucination RateSource 73.2%Not comparable
Math
BenchmarkMiMo-V2.5Muse SparkResult
FrontierMath v2 (Tiers 1-3)Source 39.000%Not comparable
FrontierMath v2 (Tier 4)Source 14.600%Not comparable
MultimodalMuse Spark wins
BenchmarkMiMo-V2.5Muse SparkResult
Video-MME (with subtitle)Source 87.7%Not comparable
CharXivSource 81%86.4%Muse Spark leads
MMMU-ProSource 77.9%80.4%Muse Spark leads
Design Arena WebsiteSource 1291Not comparable
ERQASource 64.7%Not comparable
SimpleVQASource 71.3%Not comparable
ScreenSpot ProSource 84.1%Not comparable
ZeroBenchSource 33.0%Not comparable
MedXpertQA (MM)Source 78.4%Not comparable
AA-MMMU-ProSource 80.5%Not comparable
Inst. Following
BenchmarkMiMo-V2.5Muse SparkResult
AA-IFBenchSource 75.9%Not comparable
Frequently Asked Questions (4)

Which is better, MiMo-V2.5 or Muse Spark?

Muse Spark is ahead on BenchLM's BenchAlign leaderboard, 71.04 to 58.62. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 65.8% and 59%.

Which is better for coding, MiMo-V2.5 or Muse Spark?

Muse Spark has the edge for coding in this comparison, averaging 67.8 versus 56.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiMo-V2.5 or Muse Spark?

MiMo-V2.5 has the edge for agentic tasks in this comparison, averaging 65.8 versus 59. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, MiMo-V2.5 or Muse Spark?

Muse Spark has the edge for multimodal and grounded tasks in this comparison, averaging 82.5 versus 79. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 21, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.