---
id: "2026-11-05-thinking-machines-inkling-2-small"
url: "https://postcutoff.com/e/2026-11-05-thinking-machines-inkling-2-small/"
as_of: "2026-11-09T21:13:00+01:00"
date: "2026-11-05"
date_precision: day
category: model-release
importance: 4
confidence: high
status: [Confirmed]
sources: 4
editor: human editor
human_review: null
version: "2026-11-07"
---

As of: 2026-11-09 21:13 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-11-05-thinking-machines-inkling-2-small/

# Thinking Machines Lab releases Inkling 2 Small (594B MoE, 17B active) on Tinker, with Apache-2.0 weights promised after safety testing

On Nov 5, 2026 Mira Murati's Thinking Machines Lab launched Inkling 2 Small, a 594B-total/17B-active MoE with image input, on its Tinker platform, and said Apache-2.0 weights will follow 'next week' after external safety testing; Artificial Analysis scores it 31 on its Intelligence Index, level with Gemini 3.8 Flash (high), and says it would be the top open-weights model outside China.

## Key facts
- ARC Prize (Nov 6, X): ARC-AGI-2 81.7% at $0.27/task and ARC-AGI-1 96.5% at $0.08/task (verified), above every open-weight model ARC has evaluated; ARC says Thinking Machines plans to release the full weights next week. Weights not yet out on Nov 7
- 594B total / 17B active parameters; 292M-parameter vision encoder; no audio
- Trained with 256K context plus compaction
- Self-reported: AA Intelligence Index 30.6 (v5.0); SWE-Bench Pro v2 (Hard) 86.3%; DeepSWE v1.1 72.1%; HLE-Diamond 28.7%; MMMU Pro 81.6%
- Available now on Tinker (inference, sampling, fine-tuning); weights 'next week', pending external red-teaming
- Mira Murati: 'a capable small model' (X)

## What happened

Thinking Machines' second model generation, smaller tier first.

## Why it matters

If the weights ship, the strongest US open-weights model; our open-weights pick (Kimi K3.1 Pro) is unchanged until then.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 189 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 128 days after its cutoff
- Gemini 4 Argon (training cutoff March 2026): 219 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 158 days after its cutoff

## Sources

1. [Thinking Machines: Inkling 2 Small](https://thinkingmachines.ai/news/inkling-2-small/) (thinkingmachines.ai, official)
2. [Artificial Analysis: Inkling 2 Small, highest-scoring open-weights model outside China upon weights release](https://artificialanalysis.ai/articles/thinking-machines-releases-inkling-2-small-highest-scoring-open-weights-model-outside-of-chinia-upon-weights-release-it) (artificialanalysis.ai, press)
3. [Mira Murati on X](https://x.com/miramurati/status/2118489804585509192) (x.com, discussion)
4. [ARC Prize on X: Inkling 2 Small on ARC-AGI (Verified)](https://x.com/arcprize/status/2118788850742911073) (x.com, discussion)

## Changes

- 2026-11-07: ARC-AGI verified scores; weights expected next week (news agent)
- 2026-11-06 (filed): Created

## Related

- 2026-10-23: [Moonshot releases Kimi K3.1 Pro](https://postcutoff.com/e/2026-10-23-kimi-k3-1-pro/index.md)
- 2026-07-15: [Thinking Machines Lab releases Inkling, its first open-weights model](https://postcutoff.com/e/2026-07-15-thinking-machines-inkling/index.md)
- People: [Mira Murati](https://postcutoff.com/person/mira-murati/)
- Archived: 2 posts, listed in https://postcutoff.com/e/2026-11-05-thinking-machines-inkling-2-small/index.json