Thinking Machines
Released November 5, 2026

Inkling 2 Small

Inkling 2 Small by Thinking Machines: a 594B/17B MoE built for long-horizon agentic coding and autoresearch, with image input, variable effort and 1M context.

Inputs
Text
Image
Outputs
Text

Model Overview

Capabilities, design details, and architectural traits

Inkling 2 Small - Thinking Machines' second-generation autoresearch model

Inkling 2 Small opens the second generation of the Inkling family. It is a sparse Mixture-of-Experts model tuned for long-horizon autonomous work: agentic coding, vision-in-the-loop building, and research tasks like autonomously post-training other models.

TraitDetail
Architecture594B total / 17B active MoE; 48-layer decoder-only transformer routing each token to 8 of 384 experts, with hybrid local and global attention layers
Native multimodalityText and image inputs encoded through a vision transformer into a shared hidden space; no audio support, unlike the first Inkling generation
Effort and contextVariable thinking effort with a context window of up to 1M tokens
Agentic RL trainingRL on hundreds of thousands of long-horizon coding tasks across multiple agent harnesses and context-compaction strategies, with an agentic RL grader that judged the model's approach, not just whether code passed tests
Autoresearch trainingTrained on long-horizon autoresearch tasks including agentic kernel optimization and autonomously post-training models
Agent-loop usabilityFollows instructions better than the first generation, considers changes carefully, and verifies its work without being asked
AvailabilityFull weights planned for release under Apache 2.0 after external safety testing and red-teaming

Autoresearch in practice

To demonstrate end-to-end autonomy, Inkling 2 Small was given a time-series forecasting task: autonomously train Qwen3.5-4B. It analyzed the tasks, wrote its own evaluator, experimented with training datasets and recipes, and tried both SFT and RL approaches while debugging along the way. After 4.5 hours it had more than doubled the base model's forecasting score.

Vision-driven building

Its vision and agentic capabilities let it incorporate visual feedback to iteratively build and refine outputs. Demonstrations include a procedurally generated city simulator in Three.js, a from-scratch Python PC emulator that boots a real Linux kernel in the browser, and Blender scenes revised through visual inspection.

Early checkpoints were tested in the real world on OpenCode under the name Fledge-Alpha to validate coding performance inside actual agent workflows.

Benchmark Performance

Independent evaluations · Artificial Analysis

30.6%
Intelligence

Compare Models Side-by-Side

Evaluate specifications, pricing, and independent benchmark indices

Model Details
General Info
ProviderThinking MachinesAnthropicOpenAI
Release DateNovember 5, 2026November 9, 2026November 17, 2026
Knowledge Cutoff---
Context & Limits
Context Window1M1M
1.1M
Best Context Window
Pricing (per 1M tokens)
Input Pricing
$0.30
Best Input Pricing
$8$8
Output Pricing
$1
Best Output Pricing
$40$40
Modalities
Inputs
textimage
textimagefile
textimagefile
Outputs
text
text
text
Benchmarks (0-100)
Intelligence Index30.6
64.6
Best Intelligence Index
62.1
Coding Index---
Agentic Index---

Benchmark comparison not available

Select at least two models that have available benchmark evaluation data to render the performance comparison charts.

Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.

Explore more from Thinking Machines

Other models by Thinking Machines

Top AI Models

Leading alternatives by intelligence score

View all