Technical community evaluates benchmarks and transparency
2 Sep 21 4:30 PM · 4d ago · 1 post · 5 comments · 2 sources · development 2 of 4
Commenters on Hacker News analyze MiMo v2.6's performance across Terminal Bench 4.0 and ExploitGym benchmarks, comparing it to GPT-6 Astra, Claude Fable 5.1, and other models. Reviewers praise Xiaomi's transparency in sharing training data and methodologies.
“I really like how transparent they've been about the training of this model. The realtime dashboard they shared during training was an incredible learning and teaching tool for me…”
rao-vXiaomi Model developer and publisherrao-v Hacker News commenteruser43928 Hacker News commenterlwansbrough Hacker News commenter
The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 5 voices · verbatim
-
I know we have strong views on what a truly open model is (open weights, open training data, open training code etc.) but I really like how transparent they’ve been about the training of this model.The realtime dashboard they shared during training (https://mimo.xiaomi.com/rl/) was an incredible learning and teaching tool for me, and they’ve been…
-
Flash[1]: 309B total / 15B activated parametersPro [2]:, 1.02T total / 42B activated parameters[1]:
-
Looking at the frontend design examples; why do these models seem to love the "01 - UPPERCASE TEXT" motif. It's everywhere now (see https://try.cloudflare.com/, which has '01 · QUICK TUNNELS', but no "02" anywhere).
-
Wow, the chinese labs are getting good at advertising model releases. The moat is thin.Some features of the release I like:- Demonstration of diverse tasks, such as using a DAW- Graphs from various benchmarks and price ranges- Real world use of the model in scientific environments
-
All these new models are such tease for us folks with 128GB of shared memory. Buying another unit now to expand to 256GB is a mortgage payment but it’s getting tempting…
All 4 developments of Xiaomi releases MiMo v2.6 with two model sizes →
Hacker NewsMastodonNewswiresX