Grok 4.1 Thinking Steals #1 Spot on LMArena, Surpassing Google Gemini 2.5 Pro

Grok 4.1 Thinking Steals #1 Spot on LMArena, Surpassing Google Gemini 2.5 Pro reports that Elon Musk’s xAI released two Grok 4.1 variants—the standard Grok 4.1 and the deep-reasoning-enabled Grok 4.1 Thinking—which are now freely available to users. On the LMArena leaderboard, Grok 4.1 Thinking debuted at the top with an Elo score of 1483, while the non-reasoning Grok 4.1 took second place.

Google’s Gemini 2.5 Pro has slipped to third, trailing Grok 4.1 Thinking by a full 31 points ahead of Google’s forthcoming Gemini 3.0 release. According to Creative Writing v3 benchmark results, both Grok 4.1 Thinking and Grok 4.1 rank just beneath OpenAI’s GPT 5.1, beating several competitors in creative writing.

The article also notes notable improvements in accuracy, with factual error rates falling by roughly 70% versus the previous Grok 4 Fast, and hallucinations dropping from 12.09% to 4.22%, strengthening practicality and reliability. November 19 2025.