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

Muse Glimmer 30B vs Step 5 Preview

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

4 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Meta logo
Model A
Muse Glimmer 30B

Meta

44.84/100

Estimated · Public rank #162

90% interval 33.3–56.4

StepFun logo
Model B
Step 5 Preview

StepFun

—

Evidence status unavailable

90% interval unavailable

Updated September 21, 2026. We do not rank this pair: at least one has no public score. 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

    Step 5 Preview

    Step 5 Preview 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

    Step 5 Preview 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

    Step 5 Preview is not ranked on the public lane for agentic, so no winner is named for agentic.

    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. Muse Glimmer 30B does not fit this workload in one request. Muse Glimmer 30B 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

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.

48.6Muse Glimmer 30B—Step 5 Preview

Not comparable · BenchAlign

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.

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
4
Muse Glimmer 30B only
10
Step 5 Preview only
18
Like-for-like categories
0 / 8

1 category rests 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.

Multimodal

Directional only
Muse Glimmer 30B
46.3
#41/49
Step 5 Preview
61.2
#28/49
Basis
Provisional lane · 2 vs 2 weighted rows
Reading
Directional only

Agentic

Not comparable
Muse Glimmer 30B
43.4
Estimated · #104/154
Step 5 Preview
Not ranked
Basis
BenchAlign lane · 4 vs 11 public rows
Reading
Not comparable

Coding

Not comparable
Muse Glimmer 30B
48.6
Estimated · #74/156
Step 5 Preview
Not ranked
Basis
BenchAlign lane · 4 vs 6 public rows
Reading
Not comparable

Reasoning

Not comparable
Muse Glimmer 30B
78.3
Unranked · 2 rankable rows
Step 5 Preview
78.5
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Muse Glimmer 30B
47.4
Estimated · #100/186
Step 5 Preview
Not ranked
Basis
BenchAlign lane · 0 vs 2 public rows
Reading
Not comparable

Multilingual

Not comparable
Muse Glimmer 30B
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Muse Glimmer 30B
77.7
#55/124
Step 5 Preview
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Muse Glimmer 30B
75.4
Unranked · 1 rankable row
Step 5 Preview
Not ranked
Basis
Provisional lane · 1 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.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

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

Muse Glimmer 30B
Self-hosted; infrastructure cost varies
Fits in one request
Step 5 Preview
$0.00235
Fits in one request

Muse Glimmer 30B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Muse Glimmer 30B
Self-hosted; infrastructure cost varies
Fits in one request
Step 5 Preview
$0.0581
Fits in one request

Muse Glimmer 30B has no comparable published API token rate.

Cache-heavy agent loop

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

Muse Glimmer 30B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable
Step 5 Preview
$0.057
Fits in one request

Muse Glimmer 30B does not fit this workload in one request. Muse Glimmer 30B 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.

Muse Glimmer 30B

No comparable hosted API rate

Step 5 Preview

$0.05 per 1M cached input tokens

StepFun pricing and rate limits

Reasoning profile

Muse Glimmer 30B

Reasoning

Step 5 Preview

Reasoning

Weight access

Muse Glimmer 30B

Open Weight

Step 5 Preview

Pending

License

Muse Glimmer 30B

Open Weight

Step 5 Preview

Pending

Release date

Muse Glimmer 30B

2026-08-10

Step 5 Preview

2026-09-20

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
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Step 5 Preview 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 evidence32 rows

Agentic

  • MCP Atlas

    Muse Glimmer 30B75.5%
    Source
    Step 5 Preview85.6%
    Source

    Step 5 Preview leads this result

  • DeepSearchQA

    Muse Glimmer 30B74.6%
    Source
    Step 5 Preview—

    Not directly comparable

  • skillsBench

    Muse Glimmer 30B44.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • OSWorld-Verified

    Muse Glimmer 30B65.9%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1

    Muse Glimmer 30B—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    Muse Glimmer 30B—
    Step 5 Preview33.30%
    Source

    Not directly comparable

  • CyberGym

    Muse Glimmer 30B—
    Step 5 Preview84.7%
    Source

    Not directly comparable

  • AutomationBench

    Muse Glimmer 30B—
    Step 5 Preview44.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Muse Glimmer 30B—
    Step 5 Preview74.1%
    Source

    Not directly comparable

  • JobBench

    Muse Glimmer 30B—
    Step 5 Preview59.0%
    Source

    Not directly comparable

  • APEX-Agents

    Muse Glimmer 30B—
    Step 5 Preview37.8%
    Source

    Not directly comparable

  • DRACO

    Muse Glimmer 30B—
    Step 5 Preview83.3%
    Source

    Not directly comparable

  • BrowseComp

    Muse Glimmer 30B—
    Step 5 Preview88.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Muse Glimmer 30B—
    Step 5 Preview29.5%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    Muse Glimmer 30B51.2%
    Source
    Step 5 Preview—

    Not directly comparable

  • SWE-bench Verified

    Muse Glimmer 30B76%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1

    Muse Glimmer 30B51.7%
    Source
    Step 5 Preview85.0%
    Source

    Step 5 Preview leads this result

  • SciCode

    Muse Glimmer 30B43.6%
    Source
    Step 5 Preview58.9%
    Source

    Step 5 Preview leads this result

  • DeepSWE

    Muse Glimmer 30B—
    Step 5 Preview67.7%
    Source

    Not directly comparable

  • ProgramBench

    Muse Glimmer 30B—
    Step 5 Preview80.5%
    Source

    Not directly comparable

  • sweMarathon

    Muse Glimmer 30B—
    Step 5 Preview72.7%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Muse Glimmer 30B—
    Step 5 Preview40.5%
    Source

    Not directly comparable

Reasoning

  • CritPt

    Muse Glimmer 30B—
    Step 5 Preview20.9%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    Muse Glimmer 30B78.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • ScreenSpot Pro

    Muse Glimmer 30B75.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • OmniDocBench 1.5

    Muse Glimmer 30B75.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • MMMU-Pro

    Muse Glimmer 30B74%
    Source
    Step 5 Preview76%
    Source

    Step 5 Preview leads this result

  • OfficeQA Pro

    Muse Glimmer 30B—
    Step 5 Preview60.3%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Muse Glimmer 30B—
    Step 5 Preview93.5%
    Source

    Not directly comparable

  • HLE

    Muse Glimmer 30B—
    Step 5 Preview46.5%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Muse Glimmer 30B77%
    Source
    Step 5 Preview—

    Not directly comparable

Math

  • AIME26

    Muse Glimmer 30B94.7%
    Source
    Step 5 Preview—

    Not directly comparable

Questions

Which is better, Muse Glimmer 30B or Step 5 Preview?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Muse Glimmer 30B or Step 5 Preview?

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

Which is better for agentic tasks, Muse Glimmer 30B or Step 5 Preview?

Step 5 Preview is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Muse Glimmer 30B or Step 5 Preview?

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, Muse Glimmer 30B or Step 5 Preview?

Step 5 Preview has the larger documented context window: 1M, compared with 131K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 21, 2026

Watch Muse Glimmer 30B vs Step 5 Preview

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

Read a sample issue

Join 2,000+ readers.