Thinking Machines

Inkling 2 Mini

Intelligence
20.1
Rank 288 of 813 measured models
Output speed
280 t/s
Rank 17 of 476 measured models
Context window
1.02M
Rank 111 of 1420 measured models
Cost per task
$0.587
Rank 127 of 255 measured models

Inkling 2 Mini is a text AI model from Thinking Machines, released on Nov 20, 2026, with a context window of 1.02M tokens. Its weights are openly published. Inkling 2 Mini scores 20.1 on the Artificial Analysis Intelligence Index, ranking 288th of 813 measured models. The closest models on this index are o3 (20.2), Ling 3.0 Flash (20.1), and Qwen3.8 27B (20.1). With an output speed of 280 t/s, it is faster than o3 (114 t/s), Ling 3.0 Flash (143 t/s), and Qwen3.8 27B (57.2 t/s). Every benchmark side by side: Inkling 2 Mini vs Ling 3.0 Flash.

Artificial Analysis Indices

Intelligence20.1
Rank 288 of 813 measured models

Capability indexes

Performance in specific industries, measured by Artificial Analysis
Finance & Accounting35.3
Rank 137 of 283 measured models
Strategy & Ops35.2
Rank 155 of 283 measured models
Legal31.0
Rank 151 of 283 measured models
Engineering27.6
Rank 166 of 281 measured models
Economics33.0
Rank 166 of 289 measured models

Models at a similar level

The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy