Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d257Policy30d64, 14 pendingSources1,010

Inkling-Small

Thinking MachinesReleased Jul 30, 2026Current

Score basis

Inkling-Small is capable in long context, instruction following, and reasoning; and behind the leaders in agentic tasks, coding, multimodal tasks, factuality, and math. Too few results yet to rate safety or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Capable3 capabilities
  1. Long Context−18.4%1 of 3
  2. Instruction Following−19.6%1 of 3
  3. Reasoning−23.3%4 of 6
Limited5 capabilities
  1. Agentic−28.6%6 of 7
  2. Coding−30.6%5 of 10
  3. Multimodal−31.7%2 of 6
  4. Factuality−36.4%3 of 4
  5. Math−44.7%2 of 5
Not rated2 capabilities

Too few results yet to rate Safety or Multilingual.

Price

$0.30input$1.20outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Cheaper than 59% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

71results on48benchmarks

  • 18 independently verified
  • 16 aggregator
  • 37 vendor-reported

From 12 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingReasoning

As listed by OpenRouter

Inkling-Small benchmark results

71 results on 48 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

CapableFull long context ranking

18.4% behind the leader1 of 3 ranked benchmarks measured

Instruction Following

CapableFull instruction following ranking

19.6% behind the leader1 of 3 ranked benchmarks measured

Reasoning

CapableFull reasoning ranking

23.3% behind the leader4 of 6 ranked benchmarks measured

Show 10 more reasoning resultsHide 10 reasoning results

Agentic

LimitedFull agentic ranking

28.6% behind the leader6 of 7 ranked benchmarks measured

Show 1 more agentic resultHide 1 agentic result

Coding

LimitedFull coding ranking

30.6% behind the leader5 of 10 ranked benchmarks measured

Show 2 more coding resultsHide 2 coding results

Multimodal

LimitedFull multimodal ranking

31.7% behind the leader2 of 6 ranked benchmarks measured

Show 2 more multimodal resultsHide 2 multimodal results

Factuality

LimitedFull factuality ranking

36.4% behind the leader3 of 4 ranked benchmarks measured

Show 1 more factuality resultHide 1 factuality result

Math

LimitedFull math ranking

44.7% behind the leader2 of 5 ranked benchmarks measured

Show 2 more math resultsHide 2 math results

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 24 more resultsHide 24 results

Inkling-Small: common questions

Who makes Inkling-Small?

Inkling-Small is made by Thinking Machines.

When was Inkling-Small released?

Inkling-Small was released on Jul 30, 2026, according to Thinking Machines's own announcement.

What is Inkling-Small good at?

Inkling-Small is capable in long context, instruction following, and reasoning; and behind the leaders in agentic tasks, coding, multimodal tasks, factuality, and math. Too few results yet to rate safety or multilingual tasks.

How much does Inkling-Small cost?

Inkling-Small costs $0.30 per million input tokens and $1.20 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it is cheaper than 59% of the 331 priced models we track.

How many benchmarks has Inkling-Small been tested on?

We track 71 results for Inkling-Small on 48 benchmarks from 12 sources, 18 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Inkling-Small support?

OpenRouter lists tool calling and reasoning for Inkling-Small.

About this record

Where Inkling-Small's numbers come from, and every name it appears under.

Tracked since
Jul 16, 2026
Newest source mention
Sep 13, 2026

Where the results come from

Verification: 71 scores · 18 independently verified · 16 aggregator-attributed · 37 vendor-reported. How these tiers are assigned

From 12 sources on 8 sites. api.llm-stats.com supplies 20 of them; the 18 independently verified results come from 4 sites. Bars are coloured by trust tier.

  • api.llm-stats.com20
  • artificialanalysis.ai16
  • thinkingmachines.ai14
  • arcprize.org12
  • epoch.ai3
  • huggingface.co3
  • datasets-server.huggingface.co2
  • labs.scale.com1

Also known as

How our sources name Inkling-Small at each reasoning setting.

SettingShort form
minimalinkling small (minimal)
lowinkling small (low)
mediuminkling small (medium)
highinkling small (high)
xhighinkling small (xhigh)
Also listed asthinkingmachines/inkling-smallinkling small (none)unsloth/inkling-small-ggufinkling-small:freeinkling-small:batchthinking machines inkling small