Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Hy3 Preview vs Muse Spark 1.2

Decision reading

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 resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Tencent logo
Model A
Hy3 Preview

Tencent

55.71/100

Estimated · Public rank #92

90% interval 44.2–67.2

Meta logo
Model B
Muse Spark 1.2

Meta

70.28/100

Estimated · Public rank #16

90% interval 58.9–76.0

Updated September 18, 2026. Rank says Muse Spark 1.2 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export

Share on XLinkedInSocial cardCSVJSON

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 1.2

    Muse Spark 1.2 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

    Hy3 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    Hy3 Preview 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

    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

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.

44.6Hy3 Preview60.0Muse Spark 1.2

Directional only · BenchAlign

Muse Spark 1.2 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.

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

Open the coding leaderboardShortlist models for this job

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
Hy3 Preview only
6
Muse Spark 1.2 only
8
Like-for-like categories
0 / 8

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

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

Agentic

Directional only
Hy3 Preview
48.1
Estimated · #70/154
Muse Spark 1.2
61.0
Supported · #16/154
Basis
BenchAlign lane · 2 vs 2 public rows
Reading
Directional only

Coding

Directional only
Hy3 Preview
44.6
Estimated · #96/154
Muse Spark 1.2
60.0
Supported · #21/154
Basis
BenchAlign lane · 2 vs 5 public rows
Reading
Directional only

Knowledge

Directional only
Hy3 Preview
49.2
Estimated · #88/184
Muse Spark 1.2
70.7
Estimated · #10/184
Basis
BenchAlign lane · 2 vs 1 public rows
Reading
Directional only

Reasoning

Not comparable
Hy3 Preview
Not ranked
Muse Spark 1.2
75.3
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Hy3 Preview
Not ranked
Muse Spark 1.2
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Hy3 Preview
Not ranked
Muse Spark 1.2
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Hy3 Preview
Not ranked
Muse Spark 1.2
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Hy3 Preview
46.9
#86/124
Muse Spark 1.2
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

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

Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Muse Spark 1.2
$0.00338
Fits in one request

Hy3 Preview has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Muse Spark 1.2
$0.07525
Fits in one request

Hy3 Preview has no comparable published API token rate.

Cache-heavy agent loop

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

Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable
Muse Spark 1.2
$0.0975
Fits in one request

Hy3 Preview 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.

Cached-input rate

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

Hy3 Preview

No comparable hosted API rate

Muse Spark 1.2

$0.15 per 1M cached input tokens

Meta: Muse Spark 1.2 model page

Documented inputs

Hy3 Preview

Not sourced

Muse Spark 1.2

Not sourced

Documented outputs

Hy3 Preview

Not sourced

Muse Spark 1.2

Not sourced

Provider availability

Hy3 Preview

Not sourced

Muse Spark 1.2

Not sourced

Reasoning profile

Hy3 Preview

Reasoning

Muse Spark 1.2

Reasoning

Weight access

Hy3 Preview

Open Weight

Muse Spark 1.2

Proprietary

License

Hy3 Preview

Open Weight

Muse Spark 1.2

Proprietary

Release date

Hy3 Preview

2026-04-23

Muse Spark 1.2

2026-08-05

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
Muse Spark 1.2 has the larger documented window (1M).

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 evidence14 rows

Agentic

  • Terminal-Bench 2.0

    Hy3 Preview54.4%
    Source
    Muse Spark 1.2—

    Not directly comparable

  • Gert Labs

    Hy3 Preview36.91%
    Source
    Muse Spark 1.2—

    Not directly comparable

  • Terminal-Bench 2.1

    Hy3 Preview—
    Muse Spark 1.282.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Hy3 Preview—
    Muse Spark 1.269.7%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Hy3 Preview74.4%
    Source
    Muse Spark 1.2—

    Not directly comparable

  • Terminal-Bench 2.0

    Hy3 Preview54.4%
    Source
    Muse Spark 1.2—

    Not directly comparable

  • Terminal-Bench 2.1

    Hy3 Preview—
    Muse Spark 1.282.9%
    Source

    Not directly comparable

  • DeepSWE

    Hy3 Preview—
    Muse Spark 1.259.3%
    Source

    Not directly comparable

  • VulcanBench v3

    Hy3 Preview—
    Muse Spark 1.287.0%
    Source

    Not directly comparable

  • FrontierSWE v2

    Hy3 Preview—
    Muse Spark 1.212.0%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Hy3 Preview—
    Muse Spark 1.286.6%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Hy3 Preview87.2%
    Source
    Muse Spark 1.2—

    Not directly comparable

  • GPQA-D

    Hy3 Preview87.2%
    Source
    Muse Spark 1.2—

    Not directly comparable

  • MMLU-Pro (Vals)

    Hy3 Preview—
    Muse Spark 1.288.3%
    Source

    Not directly comparable

Questions

Which is better, Hy3 Preview or Muse Spark 1.2?

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, Hy3 Preview or Muse Spark 1.2?

Muse Spark 1.2 scores higher for coding on the public lane, 60 to 44.6. Hy3 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Hy3 Preview or Muse Spark 1.2?

Muse Spark 1.2 scores higher for agentic tasks on the public lane, 61 to 48.1. Hy3 Preview 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, Hy3 Preview or Muse Spark 1.2?

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, Hy3 Preview or Muse Spark 1.2?

Muse Spark 1.2 has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 18, 2026

Watch Hy3 Preview vs Muse Spark 1.2

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

Read a sample issue

Join 2,000+ readers.