@ChrisGPT
 
DeepSeek V4 Pro 0813 is out today too!
 
DeepSeek reports jumps from 72.1% to 87.9% on Terminal-Bench 2.1, 52.7% to 83.3% on CyberGym, and 12.8% to 62.7% on DeepSWE!!
 
It costs $0.435/M input and $0.87/M output with a 1M-token context window.
 
I don’t like how every company report very separate benchmarks every time.. So I guess we will have to rely on the index.