gemini-4IMAGE

Gemini 4 Argon 在 Arena 智能体榜落后

Gemini 4 Argon 上线 Arena 智能体排行榜，净提升 +7.57%，低于 Claude Fable 5.1 Max 的 +14.31%、Opus 5.5 High 的 +13.82% 和 GPT-6.1 Sol。

Stats Wire

@StatsWire26 天前收录原推发布于 2026.10.04

Stats Wire @StatsWire原推发布于 2026.10.04

Gemini 4 Argon is live on Arena’s agent leaderboard. Gemini 4 Argon: +7.57% net improvement. Claude Fable 5.1 Max: +14.31%. Opus 5.5 High: +13.82%. Even GPT-6.1 Sol is higher. The “most advanced model Google has ever built” is currently trailing the pack where it actually matters.

x.com/statswire/status/2106426552313430031采集于 2026.10.04 10:00