Kimi K3.1 Pro revealed: 2.8T-param MoE with 1M context, weights drop tomorrow
togethercompute · x · 2026-11-04
Together AI and Moonshot AI announced Kimi K3.1 Pro, with a technical webinar on Nov 4 (9 AM PT) and open weights releasing tomorrow.
- Specs: post-trained on Kimi K3; MoE with 2.8T total / 104B active params and a 1M-token context window.
- Benchmarks: Terminal-Bench 4.0 score of 63.6%, up from 17.2% on base K3.
- Focus: long-running agent workflows—context persistence across sessions, repo navigation, terminal tool orchestration, visual feedback interpretation; gains in coding, 3D creation, and financial research.
- Agenda: why K3 needed post-training, what changed in K3.1 Pro, and lessons from building Kimi K3.
More from Models
- DanielMiessler: direct weight editing achieves fine-tuning results in minutes, vastly underrated — JensHonack · 2026-11-04
- OpenAI's internal model reportedly solving problems humans couldn't — imjustnewatai · 2026-11-04
- Artificial Analysis ships CritPt v2 grading server, regrades all models with max 1-point shifts — ArtificialAnlys · 2026-11-04
- Opus 5.5 hailed as first model that 'disappears', rumors of Opus 5.6 surface — haider1 · 2026-11-04
- LLM 'fixes' to a driving network work even with weights zeroed: model wrote its own controller — kevrussell · 2026-11-04
- Leaker hints: no "Fable 5.5" or "GPT-6.2 Astra" today — but Thursday is the date — daniel_mac8 · 2026-11-04