Inkling Small

Thinking Machines · released Jul 30, 2026

Open weightsReasoningTool useVisionAudio in

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Compare this model Source listing

Specification

Context window: 524K
Max output: 262K
Knowledge cutoff: Not stated
Parameters: 266B
Licence: apache-2.0
Serving providers: 2
Moderated: No
Uptime: 100.0%

Intelligence

41.2

89th percentile

Coding

52.9

Coding Index

Agentic

31.9

Agentic Index

Output speed

49 t/s

Median across providers

Latency

570ms

Time to first token

Cost per task

$0.12

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

GPQA Diamond
89.5%
AA-LCR (long context)
69.3%
SciCode
48.7%
Humanity's Last Exam
33.3%
τ²-bench (Telecom)
18.8%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table

Evaluation	Score
GPQA Diamond	89.5%
AA-LCR (long context)	69.3%
SciCode	48.7%
Humanity's Last Exam	33.3%
τ²-bench (Telecom)	18.8%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Nex-N2-ProNex AGI
41.7
Inkling SmallThinking Machines
41.2
GPT-5.2-CodexOpenAI
41.2
Qwen3.6 Max PreviewQwen
41.1
GLM 5.1Z.ai
41.0
GPT-5.4 MiniOpenAI
40.9
GLM 5Z.ai
40.6
Qwen3.6 PlusQwen
40.5

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table

Model	Intelligence
Nex-N2-Pro	41.7
Inkling Small	41.2
GPT-5.2-Codex	41.2
Qwen3.6 Max Preview	41.1
GLM 5.1	41.0
GPT-5.4 Mini	40.9
GLM 5	40.6
Qwen3.6 Plus	40.5

Percentile among all indexed models

Intelligence89th

Coding69th

Agentic65th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens: $0.45
Output / 1M tokens: $1.2
Cached input / 1M: $0.1
Blended 3:1: $0.637

One task, estimated

$0.12

Input tokens: 50,000
Output tokens: 80,000
Profile: Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.