Skip to main content
BenchLM
Data

Inkling 2 Mini vs Step 3.5 Flash

Updated November 21, 2026. Rank says Inkling 2 Mini is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Inkling 2 Mini has the higher public point estimate, 55.9 versus 47.7. Their conditional score ranges overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Thinking Machines Lab logo

Thinking Machines Lab

55.9/100

Estimated · Public rank #69

Conditional range 46.0–65.9

Model B
StepFun logo

StepFun

47.7/100

Supported · Public rank #104

Conditional range 36.8–58.7

API price per 1M tokens

Inkling 2 Mini: $0.15 input / $0.50 output

Step 3.5 Flash: $0.10 input / $0.30 output

Context window

Inkling 2 Mini: 1M

Step 3.5 Flash: 256K

Released

Inkling 2 Mini: November 20, 2026

Step 3.5 Flash: February 1, 2026

Shared results
1
Inkling 2 Mini only
32
Step 3.5 Flash only
2
Like-for-like categories
0 / 8
Estimated: Inkling 2 Mini · Supported: Step 3.5 Flash. 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.

  • Long documents

    Prompts that approach the documented context limit

    Inkling 2 Mini

    Inkling 2 Mini has the larger documented context window.

    Confidence: documented
  • Chat turn cost

    1K fresh input + 500 output tokens

    Step 3.5 Flash

    Step 3.5 Flash 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

    Inkling 2 Mini

    Inkling 2 Mini has the lower estimated token cost for this stated workload. Step 3.5 Flash 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

    Step 3.5 Flash

    Step 3.5 Flash 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

    Inkling 2 Mini and Step 3.5 Flash are 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

    Inkling 2 Mini and Step 3.5 Flash are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

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.

53.9Inkling 2 Mini47.1Step 3.5 Flash

Directional only · BenchAlign v6.0

Inkling 2 Mini has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

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

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

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

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

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.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
Inkling 2 Mini
59.1
Estimated · #61/179
Step 3.5 Flash
50.5
Estimated · #101/179
Basis
BenchAlign v6.0 lane · 8 vs 0 public rows
Reading
Directional only

Coding

Directional only
Inkling 2 Mini
53.9
Estimated · #67/179
Step 3.5 Flash
47.1
Estimated · #107/179
Basis
BenchAlign v6.0 lane · 5 vs 2 public rows
Reading
Directional only

Reasoning

Directional only
Inkling 2 Mini
57.8
Estimated · #58/161
Step 3.5 Flash
45.5
Supported · #96/161
Basis
BenchAlign v6.0 lane · 2 vs 0 public rows
Reading
Directional only

Multimodal

Not comparable
Inkling 2 Mini
55.5
Estimated · #62/119
Step 3.5 Flash
Not ranked
Basis
BenchAlign v6.0 lane · 13 vs 0 public rows
Reading
Not comparable

Knowledge

Not comparable
Inkling 2 Mini
51.9
Estimated · #79/158
Step 3.5 Flash
Not ranked
Basis
BenchAlign v6.0 lane · 3 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
Inkling 2 Mini
54.7
Estimated · #39/87
Step 3.5 Flash
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Instruction following

Not comparable
Inkling 2 Mini
Not ranked
Step 3.5 Flash
46.3
Estimated · #90/143
Basis
BenchAlign v6.0 lane · 1 vs 0 public rows
Reading
Not comparable

Math

Not comparable
Inkling 2 Mini
Not ranked
Step 3.5 Flash
47.5
Estimated · #74/125
Basis
BenchAlign v6.0 lane · 1 vs 1 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. 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

Inkling 2 Mini
$0.0004
Fits in one request
Step 3.5 Flash
$0.00025
Fits in one request

Step 3.5 Flash has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Inkling 2 Mini
$0.009
Fits in one request
Step 3.5 Flash
$0.0059
Fits in one request

Step 3.5 Flash has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Inkling 2 Mini
$0.011
Fits in one request
Step 3.5 Flash
$0.025
Fits in one request
Cached input priced at the published list-input rate

Inkling 2 Mini has the lower modeled cost

Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Inkling 2 Mini
$2.50
per month
Step 3.5 Flash
$1.60
per month

Standard listed rates, no batch or volume discounts.

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

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 20, 2026.

Inkling 2 MiniStep 3.5 Flash

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 2 models at the same price score higher than Inkling 2 Mini. The nearest is Claude Haiku 5.5 (score 63.7, also $0.50 per 1M output tokens).
  • Step 3.5 Flash is on the efficiency frontier: no cheaper model scores at least as high.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Inkling 2 Mini on the full price vs performance chart

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.

Step 3.5 Flash

256K

Cached-input rate

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

Inkling 2 Mini

$0.015 per 1M cached input tokens

Tinker models and pricing

Step 3.5 Flash

Not published

Provider availability

Inkling 2 Mini

Not sourced

Step 3.5 Flash

Not sourced

Reasoning profile

Inkling 2 Mini

Hybrid

Step 3.5 Flash

Non-Reasoning

Weight access

Inkling 2 Mini

Open Weight

Step 3.5 Flash

Open Weight

License

Inkling 2 Mini

Open Weight

Step 3.5 Flash

Open Weight

Release date

Inkling 2 Mini

2026-11-20

Step 3.5 Flash

2026-02-01

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
Inkling 2 Mini has the higher public point estimate, 55.9 versus 47.7. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
Repository review: $0.009 vs $0.0059. Cache-heavy agent loop: $0.011 vs $0.025.
Context tradeoff
Inkling 2 Mini has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Inkling 2 Mini or Step 3.5 Flash?

Inkling 2 Mini has the higher public point estimate, 55.9 versus 47.7. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Inkling 2 Mini or Step 3.5 Flash?

Inkling 2 Mini scores higher for coding on the public lane, 53.9 to 47.1. Inkling 2 Mini and Step 3.5 Flash are 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, Inkling 2 Mini or Step 3.5 Flash?

Inkling 2 Mini scores higher for agentic tasks on the public lane, 59.1 to 50.5. Inkling 2 Mini and Step 3.5 Flash are 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, Inkling 2 Mini or Step 3.5 Flash?

For the stated presets, chat costs $0.0004 on Inkling 2 Mini and $0.00025 on Step 3.5 Flash; repository review costs $0.009 and $0.0059; the cache-heavy agent loop costs $0.011 and $0.025. Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Inkling 2 Mini or Step 3.5 Flash?

Inkling 2 Mini has the larger documented context window: 1M, compared with 256K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Inkling 2 Mini
API / mo$488
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Step 3.5 Flash
API / mo$300
Self-host / mo$6,990
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

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

Browse raw public benchmark evidence35 rows

Agentic

  • Terminal-Bench 4.0

    Inkling 2 Mini5.60%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Terminal-Bench 2.1

    Inkling 2 Mini71.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Inkling 2 Mini1.4%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • BrowseComp

    Inkling 2 Mini79%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • DeepSearchQA

    Inkling 2 Mini85.3%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • MCP Atlas

    Inkling 2 Mini82.7%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • JobBench

    Inkling 2 Mini49.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • EnterpriseOps-Gym

    Inkling 2 Mini42.00%
    Source
    Step 3.5 Flash—

    Not directly comparable

Coding

  • FrontierCode 2.0

    Inkling 2 Mini15.1%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • DeepSWE

    Inkling 2 Mini48.2%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Terminal-Bench 2.1

    Inkling 2 Mini71.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • SWE Multilingual

    Inkling 2 Mini73.7%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • SWE-bench Verified

    Inkling 2 Mini79.2%
    Source
    Step 3.5 Flash74.4%
    Source

    Inkling 2 Mini leads this result

  • LiveCodeBench v6

    Inkling 2 Mini—
    Step 3.5 Flash86.4%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Inkling 2 Mini66.9%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • MRCR v2 256K-512K

    Inkling 2 Mini46.4%
    Source
    Step 3.5 Flash—

    Not directly comparable

Multimodal

  • PerceptionBench

    Inkling 2 Mini57.5%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • MMMU-Pro

    Inkling 2 Mini74.9%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • OmniDocBench 1.6

    Inkling 2 Mini92.8%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • BabyVision

    Inkling 2 Mini53.4%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • BabyVision w/ Python

    Inkling 2 Mini88.8%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • ScreenSpot Pro

    Inkling 2 Mini76.5%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • CharXiv

    Inkling 2 Mini88.3%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • CharXiv w/o tools

    Inkling 2 Mini80.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Chartography (no tools)

    Inkling 2 Mini22.1%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • Chartography (tools)

    Inkling 2 Mini72.5%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • ZeroBench

    Inkling 2 Mini17.0%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • ZeroBench w/ Python

    Inkling 2 Mini34.0%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • MathVision

    Inkling 2 Mini89.0%
    Source
    Step 3.5 Flash—

    Not directly comparable

Knowledge

  • GPQA

    Inkling 2 Mini86.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • GPQA-D

    Inkling 2 Mini86.6%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • HLE w/o tools

    Inkling 2 Mini30.7%
    Source
    Step 3.5 Flash—

    Not directly comparable

Instruction following

  • MultiChallenge (provider reports)

    Inkling 2 Mini50.00%
    Source
    Step 3.5 Flash—

    Not directly comparable

Math

  • Apex

    Inkling 2 Mini34.4%
    Source
    Step 3.5 Flash—

    Not directly comparable

  • AIME 2025

    Inkling 2 Mini—
    Step 3.5 Flash97.3%
    Source

    Not directly comparable

35 public results · 1 shared

Watch Inkling 2 Mini vs Step 3.5 Flash

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

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026