OpenAI employees publicly accuse Grok3's Benchmark test results of being misleading

robot
Abstract generation in progress

Jinshi Data News on February 23rd, recently, an employee of OpenAI publicly accused XAI, a company owned by Elon Musk, of releasing misleading Benchmark test results for its latest AI model, Grok3. In response, Igor Babushkin, co-founder of XAI, insisted that the company did nothing wrong. XAI's charts show that both versions of Grok3 - Grok3 Reasoning Beta and Grok3 mini Reasoning - outperformed OpenAI's current strongest available model, o3-mini-high, on AIME 2025. However, OpenAI employees quickly pointed out on the X platform that XAI's charts did not include the AIME 2025 score of o3-mini-high under the 'cons@64' condition. Babushkin argued on the X platform that OpenAI had also released similar misleading Benchmark test charts in the past, although these charts were used to compare the performance of their own models.

View Original
The content is for reference only, not a solicitation or offer. No investment, tax, or legal advice provided. See Disclaimer for more risks disclosure.
  • Reward
  • 2
  • Share
Comment
0/400
Birakenewekovip
ยท 02-23 03:48
Bull Run ๐Ÿ‚
Reply0
Renatinho25vip
ยท 02-23 02:47
Invest ๐Ÿš€
Reply0
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate app
Community
English
  • ็ฎ€ไฝ“ไธญๆ–‡
  • English
  • Tiแบฟng Viแป‡t
  • ็น้ซ”ไธญๆ–‡
  • Espaรฑol
  • ะ ัƒััะบะธะน
  • Franรงais (Afrique)
  • Portuguรชs (Portugal)
  • Bahasa Indonesia
  • ๆ—ฅๆœฌ่ชž
  • ุจุงู„ุนุฑุจูŠุฉ
  • ะฃะบั€ะฐั—ะฝััŒะบะฐ
  • Portuguรชs (Brasil)