Vibeleaderboard
← All Intel
Intel / article

Thinking Machines Releases Inkling 2 Small Highest Scoring Open Weights Model Outside Of Chinia Upon Weights Release It

Source
artificialanalysis.ai
Author
Artificial Analysis articles
Date
Why it matters

Inkling 2 Small scores 31 on the Intelligence Index at $1.18 per task but uses about 150K output tokens per task. It is proprietary for now, with an undated Apache 2.0 weights release planned.

Key takeaways · AI-distilled
  • Artificial Analysis reports Inkling 2 Small's largest gains on agentic tasks: AutomationBench-AA rose from 5% to 46% and FrontierCode 2.0 from 5% to 25% compared with Inkling Small.
  • Its coding profile differs from Claude Sonnet 5.5 (medium): 25% vs. 11% on FrontierCode 2.0, but 13% vs. 30% on Terminal-Bench 4.0.
  • The rate on AA-Omniscience v1.1 fell from 61% to 27% mainly because the model answers fewer questions: its attempt rate dropped from 77% to 53% while accuracy rose only from 32% to 34%.
  • Despite using more output , it costs $1.18 per Intelligence Index task, against $7.77 for Gemini 3.8 Flash (high) and $10.02 for Claude Sonnet 5.5 (medium), which Artificial Analysis groups as similar scorers.
  • On AA-Briefcase, a long-horizon business workflow test with spreadsheets, presentations and memos, it scores 1527 Elo vs. 1439 for Claude Sonnet 5.5 (medium) and passes 50% of rubric checks, up from 20% for Inkling Small.
Terms in this piece · Glossary
  • hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
  • token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
  • open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Read the source artificialanalysis.ai
More from Artificial Analysis articles
Recommended reads
Comments

Checking sign-in…

Loading comments…