Inkling Evaluation and Positioning Revealed
natolambert · x · 2026-07-16
The post reviews Thinky Machines' new model, Inkling:
- Scale of approximately 1T parameters, with 41B active
- Licensed under Apache-2
- Benchmark performance is considered a significant leap over Nemotron Ultra (55B active); the author calls it the new best American model, supporting omni input
- However, it still slightly trails GLM 5.2 on agentic benchmarks and falls behind Kimi K 2.6 in multimodal tasks
The poster expressed clear excitement and thanked the team.
More from Models
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- Meta's Muse Agent has built-in invite code logic, hinting at free-usage expansion — testingcatalog · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Claude is no longer available for minors as Anthropic rolls out age assurance — Muhammad523 · 2026-09-11