Is Inkling better than Inkling Small?

On accuracy they are statistically tied: Inkling scored 66.2% and Inkling Small 67.5% on the same 80 questions from open datasets. Similar accuracy; Inkling Small costs less per question.

Which is cheaper, Inkling or Inkling Small?

Inkling Small is cheaper: $0.00047 per question as billed, against $0.0012. List prices: Inkling $1 in / $4.05 out, Inkling Small $0.45 in / $1.2 out per million tokens.

Which is faster, Inkling or Inkling Small?

Inkling Small is faster at 233 output tokens per second, against 118. Time to first token: 0.6 s for Inkling, 0.5 s for Inkling Small.

Which has the larger context window, Inkling or Inkling Small?

Both accept about the same amount of context: 524k and 524k tokens.

Head to head · tested 27 Oct 2026

Inkling vs Inkling Small: accuracy, speed and price

Similar accuracy; Inkling Small costs less per question.

Thinking MachinesInkling66.2% score · #31$0.0012 per question118 tok/s

Thinking MachinesInkling Small67.5% score · #28$0.00047 per question233 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: Inkling scored 66.2% and Inkling Small 67.5% on the same 80 questions, a gap within what chance alone could produce.
Inkling Small is 2.6× cheaper per question as billed ($0.00047 vs $0.0012), reasoning tokens included.
Inkling Small generates text 2.0× faster: 233 tokens per second against 118.

Which should you choose?

Choose Inkling Small for the lower cost per correct answer ($0.00069 against $0.0019) and faster streaming.

Accuracy gap -1.3 points (z = -0.17). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

Measure	Inkling	Inkling Small	Edge
Verification scoreHigher is better	66.2%	67.5%	Too close to call
Cost per questionLower is better	$0.0012	$0.00047	Inkling Small
Output speedHigher is better	118	233	Inkling Small
Time to first tokenLower is better	0.6 s	0.5 s	Similar
End-to-end response timeLower is better	5.0 s	3.6 s	Inkling Small
Tokens per questionLower is better	228	273	Inkling
Context windowHigher is better	524k	524k	Similar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Inkling first, Inkling Small second

Verification scorehigher is better

Inkling66.2%

Inkling Small67.5%

Cost per questionlower is better

Inkling$0.0012

Inkling Small$0.00047

Output speedhigher is better

Inkling118

Inkling Small233

Time to first tokenlower is better

Inkling0.6 s

Inkling Small0.5 s

End-to-end response timelower is better

Inkling5.0 s

Inkling Small3.6 s

Tokens per questionlower is better

Inkling228

Inkling Small273

Context windowhigher is better

Inkling524k

Inkling Small524k

Score vs. cost per question

Both models in color, every other model in grey

Results by subject and dataset

Questions answered correctly. Small samples: a gap of one or two questions is noise.

Subject	Questions	Inkling	Inkling Small
Science	30	21/30	24/30
Engineering	15	6/15	6/15
Medicine	11	6/11	6/11
Economics	9	8/9	7/9
Law	6	4/6	4/6
Humanities & social science	9	8/9	7/9
SuperGPQA dataset	50	27/50	28/50
MMLU-Pro dataset	30	26/30	26/30

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

Specification	Inkling	Inkling Small
Creator	Thinking Machines	Thinking Machines
Released	17 Jul 2026	30 Jul 2026
Weights	Open weights	Open weights
Reasoning	Yes	Yes
Input	text, image, audio	text, image, audio
Output	text	text
Context window	524k tokens	524k tokens
Knowledge cutoff	—	—
List price in / out per 1M	$1 / $4.05	$0.45 / $1.2
Blended price per 1M (3:1)	$1.76	$0.64
Cheapest host	Together · $1 / $4.05	DeepInfra · $0.45 / $1.2
Hosts on OpenRouter	1	1
Last tested	27 Oct 2026	26 Oct 2026

Compare any two models →

Inkling vs Inkling Small: frequently asked questions

Is Inkling better than Inkling Small?: On accuracy they are statistically tied: Inkling scored 66.2% and Inkling Small 67.5% on the same 80 questions from open datasets. Similar accuracy; Inkling Small costs less per question.
Which is cheaper, Inkling or Inkling Small?: Inkling Small is cheaper: $0.00047 per question as billed, against $0.0012. List prices: Inkling $1 in / $4.05 out, Inkling Small $0.45 in / $1.2 out per million tokens.
Which is faster, Inkling or Inkling Small?: Inkling Small is faster at 233 output tokens per second, against 118. Time to first token: 0.6 s for Inkling, 0.5 s for Inkling Small.
Which has the larger context window, Inkling or Inkling Small?: Both accept about the same amount of context: 524k and 524k tokens.