alt Hacker NewsThose 27.3% are still in the ballpark of modern models:
- Sonnet 5 - 12.4%
- Luna - 17.3%
- Grok 4.6 - 20.3%
- Sol - 37.3%
- GLM 5.3 - 41.8%
- Opus 5 - 51.8%
Replies
p1esk • yesterday at 7:46 PM
Astra is 58%. The current title says it's "rivaling Astra"
➕ show 1 reply
Readerium • yesterday at 6:30 PM
DeepSeek v4.1 Flash 31.2%
Source: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash#compa...
➕ show 1 reply
nijave • yesterday at 8:32 PM
This explains a lot about Sonnet 5.
airstrike • yesterday at 9:24 PM
So, better than Sonnet and Luna? lol
GLM 5.3 looks strange, because of this Chinese labs benchmaxx moto. So rather they have emergent abilities or...
Also a lot of questions to benchmark because opus 5 is completely useless model right now.
I think that the main problem with opus that they try to solve context size optimization problem, and that is the main reason why it speaks like alien with only one technical dictionary at hand. So why it is so good?