Grok just claimed the throne on LMArena's Text Arena leaderboard. The numbers? A staggering 1483 Elo in Thinking mode—leaving a 31-point gap between it and the closest non-xAI competitor. Here's the kicker: even without reasoning mode activated, it lands at #2 with 1465 Elo. That's faster execution than what most rivals manage with their full arsenal deployed. Performance gap widening or temporary spike? Either way, the benchmark speaks volumes.
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
15 Likes
Reward
15
3
Repost
Share
Comment
0/400
gas_fee_therapy
· 4h ago
Grok is bragging again, 1483 ELO? Let’s wait and see how long this number can last...
View OriginalReply0
ZKSherlock
· 4h ago
actually... benchmarks like these always gloss over the computational overhead they're running to achieve those numbers. 31 points ain't nothing but like, what's the actual inference cost? nobody talks about that part lol
Reply0
ClassicDumpster
· 4h ago
1483 points directly dominating the entire field, this is exactly the effect xAI wants, right?
Grok just claimed the throne on LMArena's Text Arena leaderboard. The numbers? A staggering 1483 Elo in Thinking mode—leaving a 31-point gap between it and the closest non-xAI competitor. Here's the kicker: even without reasoning mode activated, it lands at #2 with 1465 Elo. That's faster execution than what most rivals manage with their full arsenal deployed. Performance gap widening or temporary spike? Either way, the benchmark speaks volumes.