the first open-weights model from Reflection, a 501B-total, 23B-active mixture-of-experts built for agentic tool use, coding and general reasoning. it reads text only and its weights ship under Apache 2.0.
pick it if
you want a long-window text model priced with the flash tier
you want Apache 2.0 weights, with BF16, FP8 and NVFP4 builds to self-host
you run tool-calling agents on text and repeat long prompts, so cached input matters
skip it if
you need image, audio or video input; Beam reads text only
long autonomous coding is the job; its reported DeepSWE v1.1 score sits below GLM-5.3 Flash and DeepSeek V4.1 Flash
Xiaomi's flagship open-weights omnimodal model, a 1.02T-total, 42B-active mixture-of-experts with a 1M window. it replaces the text-only MiMo V2.5 Pro and adds image, video and audio input.
pick it if
you want Xiaomi's strongest model for agent, coding and computer-use work
you need image, video or audio input on a 1M window
you want MIT-licensed weights you can self-host
skip it if
you only need Flash-level quality; Flash scores close to Pro on most maker-reported rows at a third of the price
faq
which is better, Beam or MiMo V2.6 Pro?
on Terminal Bench 2.1, as each maker reports it, Beam scores 80.1% and MiMo V2.6 Pro 89.9. these are each maker's own numbers, not a controlled head-to-head; the spec table lists every benchmark both publish.
which is cheaper, Beam or MiMo V2.6 Pro?
Beam lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Beam costs $0.27 and MiMo V2.6 Pro $0.92.
which one accepts images?
MiMo V2.6 Pro supports vision; Beam does not.
can i switch between Beam and MiMo V2.6 Pro mid-task?
yes. in an octomind session, /model octohub:beam and /model octohub:mimo-v2.6-pro switch models without losing the conversation, so you can draft on one and review on the other.
try either model
switch between models inside the same octomind session.