Skip to main content
BenchLM
Data

ScaleDown Extract vs Step 5 Preview

Updated October 13, 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 XLinkedInAPI/MCP

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.

Model A
ScaleDown Extract

ScaleDown

—

Evidence status unavailable

90% interval unavailable

Model B
StepFun logo
Step 5 Preview

StepFun

68.89/100

Estimated · Public rank #21

Conditional range 59.2–78.6

Shared results
0
ScaleDown Extract only
0
Step 5 Preview only
22
Like-for-like categories
0 / 8
Estimated: Step 5 Preview. 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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    ScaleDown Extract

    ScaleDown Extract has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    ScaleDown Extract

    ScaleDown Extract has the lower estimated token cost for this stated workload. ScaleDown Extract has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback
Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    ScaleDown Extract

    ScaleDown Extract has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    ScaleDown Extract 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

    ScaleDown Extract is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

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.

—ScaleDown Extract60.6Step 5 Preview

Not comparable · BenchAlign v5.8

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
Same basis rules as the category table below

What is actually comparable

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

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 v5.8 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

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
63.7
Estimated · #17/123
Basis
BenchAlign v5.8 lane · 0 vs 11 public rows
Reading
Not comparable

Coding

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
60.6
Estimated · #20/148
Basis
BenchAlign v5.8 lane · 0 vs 6 public rows
Reading
Not comparable

Reasoning

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
83.4
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
74.6
#24/54
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Knowledge

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
68.1
Supported · #22/180
Basis
BenchAlign v5.8 lane · 0 vs 2 public rows
Reading
Not comparable

Multilingual

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
ScaleDown Extract
Not ranked
Step 5 Preview
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 v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. 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

ScaleDown Extract
$0.00005
Fits in one request
Step 5 Preview
$0.00235
Fits in one request

ScaleDown Extract has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

ScaleDown Extract
$0.0025
Fits in one request
Step 5 Preview
$0.0581
Fits in one request

ScaleDown Extract has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

ScaleDown Extract
$0.011
Fits in one request
Cached input priced at the published list-input rate
Step 5 Preview
$0.057
Fits in one request

ScaleDown Extract has the lower modeled cost

ScaleDown Extract has no published cached-input rate, so cached tokens use its listed input rate.

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

Specification differences

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

Reasoning profile

ScaleDown Extract

Unspecified

Step 5 Preview

Reasoning

Weight access

ScaleDown Extract

Proprietary

Step 5 Preview

Pending

License

ScaleDown Extract

Proprietary

Step 5 Preview

Pending

Release date

ScaleDown Extract

Not sourced

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.0025 vs $0.0581. Cache-heavy agent loop: $0.011 vs $0.057.
Context tradeoff
Both models list 1M tokens per request (provider-listed).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, ScaleDown Extract or Step 5 Preview?

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, ScaleDown Extract or Step 5 Preview?

ScaleDown Extract is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, ScaleDown Extract or Step 5 Preview?

ScaleDown Extract is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, ScaleDown Extract or Step 5 Preview?

For the stated presets, chat costs $0.00005 on ScaleDown Extract and $0.00235 on Step 5 Preview; repository review costs $0.0025 and $0.0581; the cache-heavy agent loop costs $0.011 and $0.057. ScaleDown Extract has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, ScaleDown Extract or Step 5 Preview?

Both models list the same context window, 1M tokens per request (provider-listed).

Benchmark evidence

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

Browse raw public benchmark evidence22 rows

Agentic

  • Terminal-Bench 2.1

    ScaleDown Extract—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    ScaleDown Extract—
    Step 5 Preview33.30%
    Source

    Not directly comparable

  • CyberGym

    ScaleDown Extract—
    Step 5 Preview84.7%
    Source

    Not directly comparable

  • AutomationBench

    ScaleDown Extract—
    Step 5 Preview44.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    ScaleDown Extract—
    Step 5 Preview74.1%
    Source

    Not directly comparable

  • MCP Atlas

    ScaleDown Extract—
    Step 5 Preview85.6%
    Source

    Not directly comparable

  • JobBench

    ScaleDown Extract—
    Step 5 Preview59.0%
    Source

    Not directly comparable

  • APEX-Agents

    ScaleDown Extract—
    Step 5 Preview37.8%
    Source

    Not directly comparable

  • DRACO

    ScaleDown Extract—
    Step 5 Preview83.3%
    Source

    Not directly comparable

  • BrowseComp

    ScaleDown Extract—
    Step 5 Preview88.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    ScaleDown Extract—
    Step 5 Preview29.5%
    Source

    Not directly comparable

Coding

  • DeepSWE

    ScaleDown Extract—
    Step 5 Preview67.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    ScaleDown Extract—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • SciCode

    ScaleDown Extract—
    Step 5 Preview58.9%
    Source

    Not directly comparable

  • ProgramBench

    ScaleDown Extract—
    Step 5 Preview80.5%
    Source

    Not directly comparable

  • sweMarathon

    ScaleDown Extract—
    Step 5 Preview72.7%
    Source

    Not directly comparable

  • MLS-Bench Lite

    ScaleDown Extract—
    Step 5 Preview40.5%
    Source

    Not directly comparable

Reasoning

  • CritPt

    ScaleDown Extract—
    Step 5 Preview20.9%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    ScaleDown Extract—
    Step 5 Preview60.3%
    Source

    Not directly comparable

  • MMMU-Pro

    ScaleDown Extract—
    Step 5 Preview76%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    ScaleDown Extract—
    Step 5 Preview93.5%
    Source

    Not directly comparable

  • HLE

    ScaleDown Extract—
    Step 5 Preview46.5%
    Source

    Not directly comparable

22 public results · 0 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch ScaleDown Extract 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 5,500+ readers.

Last updated October 13, 2026