77 points by amai 2 hours ago | 9 comments
jbellis 59 minutes ago
It tops benchmarks because it uses them in its training data. https://x.com/eliebakouch/status/2077425801633427919
krackers 5 minutes ago
training on the test set is all you need
sva_ 54 minutes ago
Tostino 1 minute ago
That's just embarrassing. It keeps happening though.
sajithdilshan 39 minutes ago
Disappointing. Sounds like Volkswagen 2.0
skeledrew 10 minutes ago
> the facility runs entirely on renewable energy, is cooled with water from the Eisbach canal, and feeds waste heat into the surrounding Tucherpark neighborhood.

That's it right there. Show the others how it's done. Can see going forward most model training being done in winter, making for a proper resource recycling ecosystem.

mft_ 1 hour ago
Great to see more competition in this space, and especially from Europe, but... it's a shame when the benchmarks don't include the current best comparable models. They shows results against Qwen 3.5 and Gemma 3, but Qwen 3.6 and Gemma 4 have been available for ~three months.
neonstatic 5 minutes ago
I bet it's doing really well against Llama 3 :)
beklein 50 minutes ago
k__ 1 hour ago
"Fully open source model" with "Long-term, license-free availability for industry"

Nice trick to be not comparable with most other LLMs on the market, open weight or proprietary.

But I think, that's the right way.

doobiedowner 18 minutes ago
How can we get these things to fight each other for sport? Real battle bots
throwa356262 1 hour ago
I think this news is more about the infrastructure than the model.

Either way, happy to see two open models from outside the us-cn duopoly in the same week.

sajithdilshan 1 hour ago
Better late than never. Germans have entered the chat
petcat 48 minutes ago
More like Nemotron 3 with benchmaxxing enabled has (re-)entered the chat.
raychis 2 hours ago
[flagged]