Skip to main content
BenchLM
Advertise

Model comparison

Hy-MT1.5-1.8B-1.25bit vs Muse Spark

Updated August 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Hy-MT1.5-1.8B-1.25bit

Tencent Hunyuan

—

Evidence status unavailable

90% interval unavailable

Muse Spark

Meta

70.3/100

Supported · Public rank #17

90% interval 61.5–79.0

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.

0 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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

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

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

  • 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

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

    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
0
Hy-MT1.5-1.8B-1.25bit only
0
Muse Spark only
24
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
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
59.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Coding

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
67.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
42.5
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
50.4
Weighted basis
0 vs 1 rows
Reading
Not comparable

Math

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
32.9
Weighted basis
0 vs 2 rows
Reading
Not comparable

Multilingual

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
82.5
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
Hy-MT1.5-1.8B-1.25bit
Not measured
Muse Spark
Not measured
Weighted basis
0 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

Hy-MT1.5-1.8B-1.25bit
API rate not published
Fits in one request
Muse Spark
API rate not published
Fits in one request

Hy-MT1.5-1.8B-1.25bit has no comparable published API token rate. Muse Spark has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Hy-MT1.5-1.8B-1.25bit
API rate not published
Fits in one request
Muse Spark
API rate not published
Fits in one request

Hy-MT1.5-1.8B-1.25bit 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

Hy-MT1.5-1.8B-1.25bit
API rate not published
Fits in one request
Cached-input rate unavailable
Muse Spark
API rate not published
Fits in one request
Cached-input rate unavailable

Hy-MT1.5-1.8B-1.25bit 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.

Hy-MT1.5-1.8B-1.25bit

262K

Muse Spark

262K

API model ID

Hy-MT1.5-1.8B-1.25bit

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.

Hy-MT1.5-1.8B-1.25bit

No comparable hosted API rate

Muse Spark

No comparable hosted API rate

Documented inputs

Hy-MT1.5-1.8B-1.25bit

Not sourced

Muse Spark

Not sourced

Documented outputs

Hy-MT1.5-1.8B-1.25bit

Not sourced

Muse Spark

Not sourced

Provider availability

Hy-MT1.5-1.8B-1.25bit

Not sourced

Muse Spark

Not sourced

Reasoning profile

Hy-MT1.5-1.8B-1.25bit

Non-Reasoning

Muse Spark

Reasoning

Weight access

Hy-MT1.5-1.8B-1.25bit

Open Weight

Muse Spark

Proprietary

License

Hy-MT1.5-1.8B-1.25bit

Open Weight

Muse Spark

Proprietary

Release date

Hy-MT1.5-1.8B-1.25bit

2026-04-29

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Both models list 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 evidence24 rows

Agentic

  • Terminal-Bench 2.0

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark59%
    Source

    Not directly comparable

  • τ²-bench results

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark91.5%
    Source

    Not directly comparable

  • DeepSearchQA

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark74.8%
    Source

    Not directly comparable

  • CyberGym

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark43.5%
    Source

    Not directly comparable

  • Claw-Eval

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark63.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark77.4%
    Source

    Not directly comparable

  • SWE-bench Pro

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark52.4%
    Source

    Not directly comparable

  • LiveCodeBench Pro

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark80.0%
    Source

    Not directly comparable

  • Vibe Code Bench

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark19.67%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark42.5%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark89.5%
    Source

    Not directly comparable

  • HLE

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark50.4%
    Source

    Not directly comparable

  • HLE w/o tools

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark42.8%
    Source

    Not directly comparable

  • HealthBench Hard

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark42.8%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark52.6%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark39.000%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark14.600%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark86.4%
    Source

    Not directly comparable

  • MMMU-Pro

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark80.4%
    Source

    Not directly comparable

  • ERQA

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark64.7%
    Source

    Not directly comparable

  • SimpleVQA

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark71.3%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark84.1%
    Source

    Not directly comparable

  • ZeroBench

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark33.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    Hy-MT1.5-1.8B-1.25bit—
    Muse Spark78.4%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Hy-MT1.5-1.8B-1.25bit or Muse Spark?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Hy-MT1.5-1.8B-1.25bit 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, Hy-MT1.5-1.8B-1.25bit 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, Hy-MT1.5-1.8B-1.25bit 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, Hy-MT1.5-1.8B-1.25bit or Muse Spark?

Both models list the same context window, 262K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 3, 2026

Watch Hy-MT1.5-1.8B-1.25bit 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.