Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Model A
MiniCPM5-1B

OpenBMB

11.3/100

Estimated · Public rank #226

90% interval 1.4–21.2

MiniCPM5-1B vs Muse Spark

Updated August 22, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Muse Spark

Meta

70.6/100

Supported · Public rank #17

90% interval 61.0–80.2

Decision reading

Muse Spark has the higher public score, 70.6 versus 11.3, and the 90% score intervals do not overlap.

2 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    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. MiniCPM5-1B does not fit this workload in one request. MiniCPM5-1B has no comparable published API token rate. Muse Spark has no comparable published API token rate.

    Confidence: listed-rates

  • 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

What is actually comparable

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

Shared results
2
MiniCPM5-1B only
12
Muse Spark only
22
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Agentic

Not comparable
MiniCPM5-1B
Not measured
Muse Spark
59.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Coding

Not comparable
MiniCPM5-1B
Not measured
Muse Spark
67.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
MiniCPM5-1B
Not measured
Muse Spark
42.5
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
MiniCPM5-1B
44.0
Muse Spark
50.4
Weighted basis
2 vs 1 rows
Reading
Not comparable

Math

Not comparable
MiniCPM5-1B
33.1
Muse Spark
32.9
Weighted basis
2 vs 2 rows
Reading
Not comparable

Multilingual

Not comparable
MiniCPM5-1B
Not measured
Muse Spark
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
MiniCPM5-1B
Not measured
Muse Spark
82.5
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
MiniCPM5-1B
58.5
Muse Spark
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

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.

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

MiniCPM5-1B
API rate not published
Fits in one request
Muse Spark
API rate not published
Fits in one request

MiniCPM5-1B has no comparable published API token rate. Muse Spark has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

MiniCPM5-1B
API rate not published
Fits in one request
Muse Spark
API rate not published
Fits in one request

MiniCPM5-1B has no comparable published API token rate. Muse Spark has no comparable published API token rate.

Cache-heavy agent loop

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

MiniCPM5-1B
API rate not published
Does not fit in one request
Cached-input rate unavailable
Muse Spark
API rate not published
Fits in one request
Cached-input rate unavailable

MiniCPM5-1B does not fit this workload in one request. MiniCPM5-1B has no comparable published API token rate. Muse Spark has no comparable published API token rate.

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.

MiniCPM5-1B

131K

Muse Spark

262K

API model ID

MiniCPM5-1B

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.

MiniCPM5-1B

No comparable hosted API rate

Muse Spark

No comparable hosted API rate

Documented inputs

MiniCPM5-1B

Not sourced

Muse Spark

Not sourced

Documented outputs

MiniCPM5-1B

Not sourced

Muse Spark

Not sourced

Provider availability

MiniCPM5-1B

Not sourced

Muse Spark

Not sourced

Reasoning profile

MiniCPM5-1B

Reasoning

Muse Spark

Reasoning

Weight access

MiniCPM5-1B

Open Weight

Muse Spark

Proprietary

License

MiniCPM5-1B

Open Weight

Muse Spark

Proprietary

Release date

MiniCPM5-1B

2026-05-25

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 score, 70.6 versus 11.3, and the 90% score intervals do not overlap.
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.

Benchmark evidence

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

Browse raw public benchmark evidence36 rows

Agentic

  • BFCL v4

    MiniCPM5-1B25.1%
    Source
    Muse Spark—

    Not directly comparable

  • Terminal-Bench 2.0

    MiniCPM5-1B—
    Muse Spark59%
    Source

    Not directly comparable

  • τ²-bench results

    MiniCPM5-1B—
    Muse Spark91.5%
    Source

    Not directly comparable

  • DeepSearchQA

    MiniCPM5-1B—
    Muse Spark74.8%
    Source

    Not directly comparable

  • CyberGym

    MiniCPM5-1B—
    Muse Spark43.5%
    Source

    Not directly comparable

  • Claw-Eval

    MiniCPM5-1B—
    Muse Spark63.8%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    MiniCPM5-1B22.7%
    Source
    Muse Spark80.0%
    Source

    Muse Spark leads this result

  • LiveCodeBench v6

    MiniCPM5-1B33.5%
    Source
    Muse Spark—

    Not directly comparable

  • SWE-bench Verified

    MiniCPM5-1B—
    Muse Spark77.4%
    Source

    Not directly comparable

  • SWE-bench Pro

    MiniCPM5-1B—
    Muse Spark52.4%
    Source

    Not directly comparable

  • Vibe Code Bench

    MiniCPM5-1B—
    Muse Spark19.67%
    Source

    Not directly comparable

Reasoning

  • BBH

    MiniCPM5-1B71.9%
    Source
    Muse Spark—

    Not directly comparable

  • ARC-AGI-2

    MiniCPM5-1B—
    Muse Spark42.5%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    MiniCPM5-1B48.9%
    Source
    Muse Spark—

    Not directly comparable

  • MMLU-Redux

    MiniCPM5-1B70.1%
    Source
    Muse Spark—

    Not directly comparable

  • GPQA-D

    MiniCPM5-1B26.3%
    Source
    Muse Spark89.5%
    Source

    Muse Spark leads this result

  • SuperGPQA

    MiniCPM5-1B23.1%
    Source
    Muse Spark—

    Not directly comparable

  • HLE

    MiniCPM5-1B—
    Muse Spark50.4%
    Source

    Not directly comparable

  • HLE w/o tools

    MiniCPM5-1B—
    Muse Spark42.8%
    Source

    Not directly comparable

  • HealthBench Hard

    MiniCPM5-1B—
    Muse Spark42.8%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    MiniCPM5-1B—
    Muse Spark52.6%
    Source

    Not directly comparable

Math

  • AIME 2025

    MiniCPM5-1B40.4%
    Source
    Muse Spark—

    Not directly comparable

  • AIME26

    MiniCPM5-1B40.4%
    Source
    Muse Spark—

    Not directly comparable

  • HMMT Feb 2026

    MiniCPM5-1B25.8%
    Source
    Muse Spark—

    Not directly comparable

  • MATH-500

    MiniCPM5-1B91.6%
    Source
    Muse Spark—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    MiniCPM5-1B—
    Muse Spark39.000%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    MiniCPM5-1B—
    Muse Spark14.600%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    MiniCPM5-1B—
    Muse Spark86.4%
    Source

    Not directly comparable

  • MMMU-Pro

    MiniCPM5-1B—
    Muse Spark80.4%
    Source

    Not directly comparable

  • ERQA

    MiniCPM5-1B—
    Muse Spark64.7%
    Source

    Not directly comparable

  • SimpleVQA

    MiniCPM5-1B—
    Muse Spark71.3%
    Source

    Not directly comparable

  • ScreenSpot Pro

    MiniCPM5-1B—
    Muse Spark84.1%
    Source

    Not directly comparable

  • ZeroBench

    MiniCPM5-1B—
    Muse Spark33.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    MiniCPM5-1B—
    Muse Spark78.4%
    Source

    Not directly comparable

Instruction following

  • IFBench

    MiniCPM5-1B46.7%
    Source
    Muse Spark—

    Not directly comparable

  • IFEval

    MiniCPM5-1B80.4%
    Source
    Muse Spark—

    Not directly comparable

Frequently asked questions

Which is better, MiniCPM5-1B or Muse Spark?

Muse Spark has the higher public score, 70.6 versus 11.3, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, MiniCPM5-1B or Muse Spark?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, MiniCPM5-1B or Muse Spark?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, MiniCPM5-1B 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, MiniCPM5-1B or Muse Spark?

Muse Spark has the larger documented context window: 262K, compared with 131K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 22, 2026

Watch MiniCPM5-1B vs Muse Spark

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

Read a sample issue

Join 2,000+ readers.