๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

SciTech Era
@SciTechera
i write on AI, longevity, singularity, robotics, energy and the latest SciTech breakthroughs. by(@alxom17)
๊ฐ€์ž… October 2023
545 ํŒ”๋กœ์ž‰ ์ค‘    22.6K ํŒฌ
Wow. That's crazy. 105ร— cheaper than Fable 5. ๐Ÿ‘€ DeepSeek V4 Flash outperformed Claude Fable 5 on Terminal-Bench 2.1 while costing around 105ร— less per completed benchmark task. DeepSeek V4 Flash scored 82.7 on Terminal-Bench 2.1, ahead of Claude Fable 5's 80.5. According to Artificial Analysis, the estimated cost per benchmark task is just $0.03 for DeepSeek V4 Flash, compared with $3.15 for Claude Fable 5, making it about 105ร— cheaper. We're entering an era where frontier-level AI is becoming radically more affordable!
๋” ๋ณด๊ธฐ