Back to News
Advertisement
Advertisement

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 185 words in the discussion.

Trending Topics

#https#more#open#benchmarks#training#eliebakouch#status#disappointing#comparable#models

Discussion (10 Comments)Read Original on HackerNews

jbellis•about 1 hour ago
It tops benchmarks because it uses them in its training data. https://x.com/eliebakouch/status/2077425801633427919
krackers•16 minutes ago
training on the test set is all you need
sva_•about 1 hour ago
Tostino•12 minutes ago
That's just embarrassing. It keeps happening though.
sajithdilshan•about 1 hour ago
Disappointing. Sounds like Volkswagen 2.0
mft_•about 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•16 minutes ago
I bet it's doing really well against Llama 3 :)
doobiedowner•29 minutes ago
How can we get these things to fight each other for sport? Real battle bots
beklein•about 1 hour ago
k__•about 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.

throwa356262•about 2 hours 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•about 1 hour ago
Better late than never. Germans have entered the chat
petcat•about 1 hour ago
More like Nemotron 3 with benchmaxxing enabled has (re-)entered the chat.