Datenerreichbar
Thinking Machines releases Inkling 2 Small (Artificial Analysis, 5. November 2026)
artificialanalysis.ai (externe Seite)
Auswertung von Artificial Analysis mit Benchmarkwerten wie Automation
geprüft 10.11.2026
Worauf sich diese Seite beruft, wörtlich, abgerufen am 07.11.2026:
Inkling 2 Small is launching as a proprietary model, available first-party through Thinking Machines' Tinker platform
bestätigt 10.11.2026Automation
bestätigt 10.11.2026Bench-AA rises from 5% to 46% Its score is up 18 points from Inkling Small, with ~4x as many output tokens per task.
bestätigt 10.11.2026It matches Google Deep
bestätigt 10.11.2026Mind's Gemini 3.8 Flash (high) and surpasses Xiaomi's MiMo-V2.6-Pro on the Artificial Analysis Intelligence Index v5.0.1. their plan to release its weights would make it the highest-scoring open weights model developed outside China based on current rankings
bestätigt 10.11.2026Inkling 2 Small scores 25% on Frontier
bestätigt 10.11.2026Code 2.0 vs. 11% for Claude Sonnet 5.5 (medium), but 13% on Terminal-Bench 4.0 vs. 30%. Inkling 2 Small hallucinates less mainly because it answers fewer questions, while accuracy improves only slightly.
bestätigt 10.11.2026Inkling 2 Small averages ~150K output tokens per Intelligence Index task vs. ~37K for Inkling Small, ~31K for Claude Sonnet 5.5 (medium), and ~99K for Gemini 3.8 Flash (high).
bestätigt 10.11.2026Inkling 2 Small costs $1.18 per Intelligence Index task vs. $0.20 for Inkling Small, $7.77 for Gemini 3.8 Flash (high), and $10.02 for Claude Sonnet 5.5 (medium).
bestätigt 10.11.2026$0.30/$1.00 per 1M input/
bestätigt 10.11.2026output tokens ($0.03 per 1M cached input tokens) Apache 2.0 weights release planned (date unconfirmed)
bestätigt 10.11.2026