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

X Freeze
@XFreeze
๊ฐ€์ž… July 2024
2.1K ํŒ”๋กœ์ž‰ ์ค‘    277.8K ํŒฌ
Grok 4.7 xHigh just hit a remarkably low hallucination rate on Artificial Analysisโ€™ AA-Omniscience benchmark โ€ข Grok 4.7 xHigh โ€” 29% ๐Ÿ† โ€ข GPT-6 Astra โ€” 51% โ€ข Claude Fable 5.1 โ€” 73% Lower is better Grok is dramatically outperforming both Astra and Fable 5.1 on hallucination rate
๋” ๋ณด๊ธฐ