Skip to main content
BenchLM
Data

MiniMax M2.5 vs Muse Spark

Updated November 19, 2026. Rank says Muse Spark is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Muse Spark has the higher public point estimate, 53.6 versus 39. Their conditional score ranges overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
MiniMax logo

MiniMax

39/100

Supported · Public rank #158

Conditional range 28.4–49.6

Model B
Meta logo

Meta

53.6/100

Supported · Public rank #80

Conditional range 43.8–63.5

API price per 1M tokens

MiniMax M2.5: $0.30 input / $1.20 output

Muse Spark: No comparable API price

Context window

MiniMax M2.5: 128K

Muse Spark: 262K

Released

MiniMax M2.5: February 12, 2026

Muse Spark: April 8, 2026

Shared results
1
MiniMax M2.5 only
0
Muse Spark only
24
Like-for-like categories
0 / 8
Supported: MiniMax M2.5 and Muse Spark. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    Muse Spark

    Muse Spark has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    MiniMax M2.5 is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Muse Spark is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited
  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. MiniMax M2.5 does not fit this workload in one request. MiniMax M2.5 has no published cached-input rate, so cached tokens use its listed input rate. Muse Spark has no comparable published API token rate.

    Confidence: rate-fallback
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

—MiniMax M2.549.2Muse Spark

Not comparable · BenchAlign v6.0

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
MiniMax M2.5
36.9
Supported · #143/177
Muse Spark
52.9
Estimated · #84/177
Basis
BenchAlign v6.0 lane · 0 vs 5 public rows
Reading
Directional only

Coding

Not comparable
MiniMax M2.5
Not ranked
Muse Spark
49.2
Estimated · #88/177
Basis
BenchAlign v6.0 lane · 1 vs 5 public rows
Reading
Not comparable

Reasoning

Not comparable
MiniMax M2.5
39.7
Supported · #122/160
Muse Spark
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 1 public rows
Reading
Not comparable

Multimodal

Not comparable
MiniMax M2.5
Not ranked
Muse Spark
58.6
Estimated · #52/115
Basis
BenchAlign v6.0 lane · 0 vs 7 public rows
Reading
Not comparable

Knowledge

Not comparable
MiniMax M2.5
Not ranked
Muse Spark
54.6
Estimated · #65/156
Basis
BenchAlign v6.0 lane · 0 vs 7 public rows
Reading
Not comparable

Multilingual

Not comparable
MiniMax M2.5
Not ranked
Muse Spark
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Instruction following

Not comparable
MiniMax M2.5
35.7
Estimated · #124/142
Muse Spark
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Math

Not comparable
MiniMax M2.5
Not ranked
Muse Spark
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

MiniMax M2.5
$0.0009
Fits in one request
Muse Spark
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

MiniMax M2.5
$0.0186
Fits in one request
Muse Spark
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

MiniMax M2.5
$0.078
Does not fit in one request
Cached input priced at the published list-input rate
Muse Spark
API rate not published
Fits in one request
Cached-input rate unavailable

MiniMax M2.5 does not fit this workload in one request. MiniMax M2.5 has no published cached-input rate, so cached tokens use its listed input rate. Muse Spark has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 18, 2026.

MiniMax M2.5

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 18 models score at least as high as MiniMax M2.5 for the same price or less. The nearest is DeepSeek V4.1 Flash 1017 (score 69.9, also $1.20 per 1M output tokens).
  • Muse Spark has no public API price, so it is not plotted.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See MiniMax M2.5 on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

MiniMax M2.5

128K

Muse Spark

262K

API model ID

MiniMax M2.5

Not sourced

Muse Spark

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

MiniMax M2.5

Not published

Muse Spark

No comparable hosted API rate

Provider availability

MiniMax M2.5

Not sourced

Muse Spark

Not sourced

Reasoning profile

MiniMax M2.5

Non-Reasoning

Muse Spark

Reasoning

Weight access

MiniMax M2.5

Proprietary

Muse Spark

Proprietary

License

MiniMax M2.5

Proprietary

Muse Spark

Proprietary

Release date

MiniMax M2.5

2026-02-12

Muse Spark

2026-04-08

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Muse Spark has the higher public point estimate, 53.6 versus 39. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Muse Spark has the larger documented window (262K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, MiniMax M2.5 or Muse Spark?

Muse Spark has the higher public point estimate, 53.6 versus 39. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, MiniMax M2.5 or Muse Spark?

MiniMax M2.5 is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, MiniMax M2.5 or Muse Spark?

Muse Spark scores higher for agentic tasks on the public lane, 52.9 to 36.9. Muse Spark is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, MiniMax M2.5 or Muse Spark?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, MiniMax M2.5 or Muse Spark?

Muse Spark has the larger documented context window: 262K, compared with 128K.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence25 rows

Agentic

  • Terminal-Bench 2.0

    MiniMax M2.5—
    Muse Spark59%
    Source

    Not directly comparable

  • τ²-bench results

    MiniMax M2.5—
    Muse Spark91.5%
    Source

    Not directly comparable

  • DeepSearchQA

    MiniMax M2.5—
    Muse Spark74.8%
    Source

    Not directly comparable

  • CyberGym

    MiniMax M2.5—
    Muse Spark43.5%
    Source

    Not directly comparable

  • Claw-Eval

    MiniMax M2.5—
    Muse Spark63.8%
    Source

    Not directly comparable

Coding

  • Vibe Code Bench

    Shared source
    MiniMax M2.514.85%
    Muse Spark19.67%

    Muse Spark leads this result

  • SWE-bench Verified

    MiniMax M2.5—
    Muse Spark77.4%
    Source

    Not directly comparable

  • SWE-bench Pro

    MiniMax M2.5—
    Muse Spark52.4%
    Source

    Not directly comparable

  • LiveCodeBench Pro

    MiniMax M2.5—
    Muse Spark80.0%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    MiniMax M2.5—
    Muse Spark74.4%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    MiniMax M2.5—
    Muse Spark42.5%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    MiniMax M2.5—
    Muse Spark86.4%
    Source

    Not directly comparable

  • MMMU-Pro

    MiniMax M2.5—
    Muse Spark80.4%
    Source

    Not directly comparable

  • ERQA

    MiniMax M2.5—
    Muse Spark64.7%
    Source

    Not directly comparable

  • SimpleVQA

    MiniMax M2.5—
    Muse Spark71.3%
    Source

    Not directly comparable

  • ScreenSpot Pro

    MiniMax M2.5—
    Muse Spark84.1%
    Source

    Not directly comparable

  • ZeroBench

    MiniMax M2.5—
    Muse Spark33.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    MiniMax M2.5—
    Muse Spark78.4%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    MiniMax M2.5—
    Muse Spark89.5%
    Source

    Not directly comparable

  • HLE

    MiniMax M2.5—
    Muse Spark50.4%
    Source

    Not directly comparable

  • HLE w/o tools

    MiniMax M2.5—
    Muse Spark42.8%
    Source

    Not directly comparable

  • HealthBench Hard

    MiniMax M2.5—
    Muse Spark42.8%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    MiniMax M2.5—
    Muse Spark52.6%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    MiniMax M2.5—
    Muse Spark89.6%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    MiniMax M2.5—
    Muse Spark87.3%
    Source

    Not directly comparable

25 public results · 1 shared

Watch MiniMax M2.5 vs Muse Spark

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 19, 2026