bindureddy
@fzvccsfzvccsajig
LiveBench AI - Coding Category Re-Haul We have changed the coding category questions to be way more complicated. This change was made to reflect real-life coding scenarios. You will see that Sonnet scores much higher, and OpenAI's models do very well. In real life, Sonnet 3.7 https://t.co/LgmjBvHGmG
0 reply
0 recast
0 reaction