Skip to main content

Model comparison

MiMo-V2.5-Pro vs Muse Spark

Data verified

Head-to-head evidence from 20 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

70.19/100
Margin
0.9pts
winning →
71.04/100
1 category wins2 category wins

Public leaderboard positions: MiMo-V2.5-Pro #14 (Supported); Muse Spark #13 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiMo-V2.5-Pro and Muse Spark share 20 comparable benchmark results. 3 of 8 categories are comparable. 11 results are unique to MiMo-V2.5-Pro; 19 to Muse Spark.

Updated July 21, 2026
Shared results
20
MiMo-V2.5-Pro only
11
Muse Spark only
19
Comparable categories
3 / 8

Pick Muse Spark if you want the stronger benchmark profile. MiMo-V2.5-Pro 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 20 shared benchmark results across 5 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 has the cleaner BenchAlign overall profile here, landing at 71.04 versus 70.19. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Muse Spark's sharpest advantage is in coding, where it averages 67.8 against 57.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 68.4% to 59%. MiMo-V2.5-Pro does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

MiMo-V2.5-Pro 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-Pro and Muse Spark
CategoryMiMo-V2.5-ProΔMuse Spark
CodingMiMo-V2.5-Pro57.2Margin 10.6Muse Spark67.8
AgenticMiMo-V2.5-Pro68.4Margin 9.4Muse Spark59.0
KnowledgeMiMo-V2.5-Pro48.0Margin 2.4Muse Spark50.4
ReasoningMiMo-V2.5-ProNot measuredMarginNo overlapMuse Spark42.5
MathMiMo-V2.5-ProNot measuredMarginNo overlapMuse Spark32.9
MultimodalMiMo-V2.5-ProNot measuredMarginNo overlapMuse Spark82.5

Decisive benchmark drivers

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

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

    Agentic
    Source ↗
    A 68.4%B 59%
    Winner: MiMo-V2.5-ProΔ 9.4
    Terminal-Bench 2.0: MiMo-V2.5-Pro scored 68.4%; Muse Spark scored 59%. MiMo-V2.5-Pro wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 57.2%B 52.4%
    Winner: MiMo-V2.5-ProΔ 4.8
    SWE-bench Pro: MiMo-V2.5-Pro scored 57.2%; Muse Spark scored 52.4%. MiMo-V2.5-Pro wins this benchmark.
  3. HLE

    Knowledge
    Source ↗
    A 48%B 50.4%
    Winner: Muse SparkΔ 2.4
    HLE: MiMo-V2.5-Pro scored 48%; Muse Spark scored 50.4%. Muse Spark wins this benchmark.

Operational comparison

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

MetricMiMo-V2.5-ProMuse SparkComparison
Input / output priceUSD per 1M tokensMiMo-V2.5-ProNot availableMuse SparkNot availableA complete price comparison is not available.
Generation speedtokens per secondMiMo-V2.5-ProNot availableMuse SparkNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiMo-V2.5-ProNot availableMuse SparkNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiMo-V2.5-Pro1MMuse Spark262KMiMo-V2.5-Pro lists the larger context window.

Benchmark Deep Dive

AgenticMiMo-V2.5-Pro wins
BenchmarkMiMo-V2.5-ProMuse SparkResult
Claw-EvalSource 63.8%63.8%Tie
GDPval-AASource 12651144MiMo-V2.5-Pro leads
τ³-bench resultsSource 72.9%Not comparable
Terminal-Bench 2.0Source 68.4%59%MiMo-V2.5-Pro leads
AA Agentic IndexSource 29.1%28.7%MiMo-V2.5-Pro leads
τ²-bench resultsSource 94.2%91.5%MiMo-V2.5-Pro leads
GDPval-AASource 38.3%32.2%MiMo-V2.5-Pro leads
APEX-Agents-AASource 2.4%Not comparable
Gert LabsSource 62.70%Not comparable
AA BriefcaseSource 873Not comparable
AA ITBenchSource 38.2%Not comparable
terminalBenchHardSource 43.2%Not comparable
aaTerminalBench21Source 65.2%Not comparable
AA Harvey LABSource 73.3%Not comparable
DeepSearchQASource 74.8%Not comparable
CyberGymSource 43.5%Not comparable
CodingMuse Spark wins
BenchmarkMiMo-V2.5-ProMuse SparkResult
SWE-bench ProSource 57.2%52.4%MiMo-V2.5-Pro leads
Terminal-Bench 2.0Source 68.4%Not comparable
AA Coding IndexSource 60.2%58.6%MiMo-V2.5-Pro leads
AA-SciCodeSource 50.2%51.5%Muse Spark leads
SWE-bench VerifiedSource 77.4%Not comparable
LiveCodeBench ProSource 80.0%Not comparable
Vibe Code BenchSource 19.67%Not comparable
Reasoning
BenchmarkMiMo-V2.5-ProMuse SparkResult
AA-LCRSource 73.3%69.7%MiMo-V2.5-Pro leads
CritPtSource 4.0%11.3%Muse Spark leads
ARC-AGI-2Source 42.5%Not comparable
KnowledgeMuse Spark wins
BenchmarkMiMo-V2.5-ProMuse SparkResult
HLESource 48%50.4%Muse Spark leads
HLE w/o toolsSource 34%42.8%Muse Spark leads
Artificial Analysis Intelligence IndexSource 42.2%43.1%Muse Spark leads
AA-GPQA DiamondSource 86.6%88.4%Muse Spark leads
AA-HLESource 33.8%39.9%Muse Spark leads
AA-Omniscience IndexSource 3.6%4.1%Muse Spark leads
AA-Omniscience AccuracySource 22.6%44.6%Muse Spark leads
AA-Omniscience Hallucination RateSource 24.5%73.2%MiMo-V2.5-Pro leads
AA Openness IndexSource 38.9%Not comparable
GPQA-DSource 89.5%Not comparable
HealthBench HardSource 42.8%Not comparable
MedXpertQA (Text)Source 52.6%Not comparable
Math
BenchmarkMiMo-V2.5-ProMuse SparkResult
FrontierMath v2 (Tiers 1-3)Source 39.000%Not comparable
FrontierMath v2 (Tier 4)Source 14.600%Not comparable
Multimodal
BenchmarkMiMo-V2.5-ProMuse SparkResult
Design Arena WebsiteSource 1298Not comparable
CharXivSource 86.4%Not comparable
MMMU-ProSource 80.4%Not 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-V2.5-ProMuse SparkResult
AA-IFBenchSource 79.9%75.9%MiMo-V2.5-Pro leads
Frequently Asked Questions (4)

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

Muse Spark is ahead on BenchLM's BenchAlign leaderboard, 71.04 to 70.19. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 68.4% and 59%.

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

Muse Spark has the edge for knowledge tasks in this comparison, averaging 50.4 versus 48. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

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

Muse Spark has the edge for coding in this comparison, averaging 67.8 versus 57.2. 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-Pro or Muse Spark?

MiMo-V2.5-Pro has the edge for agentic tasks in this comparison, averaging 68.4 versus 59. Inside this category, GDPval-AA 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.