Gemini 4 Argon tops Text Arena at 1525 pts, 20 pts above Claude Opus 4.6, at $8/MToken
arena · x · 2026-10-06
LMArena announced that Google's Gemini 4 Argon (High) took #1 in Text Arena with 1525 points, leading coding, hard prompts, instruction following, creative writing, and every occupational domain including Chinese and Russian, plus #8 in WebDev. At a blended $8/MToken it's the most cost-efficient model, 20 points above #2 Claude Opus 4.6 (High). In the same thread, Arena CEO mlangelopoulos said she picks writing models by expert rankings because she dislikes the sycophantic style general users prefer — the reason they built style control.
Related event: Gemini 4 Argon Tops LMArena Text Arena Leaderboard(2 posts)→
More from Models
- Reflection AI debuts Beam: open agentic model with 501B total, 23B active params — bigblueboo · 2026-10-06
- Gemini 4 Argon tops Text Arena, writes a novel with 1M-token output limit — DynamicWebPaige · 2026-10-06
- Vision models beat Wordle from screenshots alone: OCR plus reasoning lands correct guesses — maximelabonne · 2026-10-06
- Google's Arohan: Gemini Nano chapter added to report, real inflection lands next year — _arohan_ · 2026-10-06
- LenVM lands COLM 2026 Spotlight: value model predicts remaining generation length for efficient reasoning — xwang_lk · 2026-10-06
- One model runs multiple games in parallel, researcher calls it bigger than LLM text generation — maximelabonne · 2026-10-06