Arena weekly: Gemini 4 Argon hits #5 in Agent Arena, Meta Muse Wonder debuts #2
arena · x · 2026-10-17
LMArena's weekly update:
- Agent Arena: Google DeepMind's Gemini 4 Argon (High) landed #5 with a +13.2% net improvement; Xiaomi's MiMo V2.6 Pro is now the #1 open model (#13 overall) with +3.9%.
- Text Arena: Meta's Muse Wonder (Max) debuted at #2 with 1513 points, plus #15 in WebDev Code Arena (1651) and #12 in Agent Arena (+6.4%).
- Muse Spark Open is live in Agent Arena, scores pending.
- Arena shipped a new agentic version of Max, its model router, achieving frontier-level performance at 37% lower cost.
More from Models
- Hermes Index adds GPT 6.1 Sol as Claude Opus 5.5 keeps agentic crown — Teknium · 2026-10-17
- GPT-6 Astra fastest-rising method on Papers with Code, 27 papers in 30 days — NielsRogge · 2026-10-17
- Sentry CEO publicly asks Anthropic for a $500 Claude plan with 3x capacity — zeeg · 2026-10-17
- Andrew Ng: AI improves fastest on verifiable tasks; judgment tasks lag far behind — DeepLearningAI · 2026-10-17
- Fable 5.5 posts standout results on VoxelBench — legit_api · 2026-10-17
- Terence Tao explains why OpenAI dumping IMO math solutions was extremely rude — kaljakin · 2026-10-17