Google's Gemini 4 Argon currently leads Text Arena math leaderboards with the highest Elo ratings from blind votes on math prompts, giving traders a slight edge in implied probability at 49.5% versus Anthropic's 36.5%. Recent releases and optimizations in Google's Gemini 4 series have strengthened its position in multi-step reasoning and competition-style problems, outpacing Anthropic's Claude Opus 5 variants that remain statistically close. Other labs like Z.ai, Alibaba's Qwen, and Meta trail further behind on arena metrics, while OpenAI models sit lower despite strong benchmark scores elsewhere. Rapid iteration in large language models means new releases or fine-tunes before end of January could shift the outcome, with traders watching for updates that improve math-specific capabilities like chain-of-thought accuracy and consistency.
基于Polymarket数据的AI实验性摘要。这不是交易建议,也不影响该市场的结算方式。 · 更新于1H6H1D7D30DALL
View resolved






















警惕外部链接哦。
警惕外部链接哦。
常见问题