MaxxBench – "Nice DeepSWE score. But is it true?"
387 punktów · 104 komentarze · autor antiuniverse · maxxbench.unlap.ai
- Punkty
- 387
- Komentarze
- 104
Więcej z tego źródła
Wszystkie-
Claude Fable 5.2 and Mythos 5.2
-
Too many men suffering in silence, national health report finds (Canada)
-
Our Smallest, Most Efficient Model: Muse Ember
-
When will this stop? The Raspberry Pi 5 16GB SBC now sells for $385
-
Going back two years on Hacker News is like entering another, better universe
-
Payments Canada announces launch of Canada's Real-Time Rail (RTR) payment system
-
The same H100 costs $2.69 or $12.29 an hour depending where you rent it
-
Cryptocurrency lawsuit: Ethereum Foundation required "suicide pledge"