Gemini 4 Neon ranks #2 on Agent Arena, beats Opus 5.5 at 53% lower cost per task
melvinjohnsonp · x · 2026-11-19
LMArena announces Gemini 4 Neon (High) as the best-ranked Google model on the Agent Arena Index, #2 overall at 1336 pts, reshaping the Pareto frontier based on 4.2k real-world agentic sessions:
- Surpasses #4 Carbon (High) at 1303, #9 Hydrogen (High) at 1271, and #11 Argon (High) at 1229
- $2.82 median cost per task; scores higher than #3 Claude Opus 5.5 (Max) at 53% less per task, and 69% less than #1 Claude Fable 5.2 (Max)
- Strong sub-scores: #2 in Praise vs. Complaint (1539, user satisfaction) and #2 in Steerability (1298)
Poster melvinjohnsonp adds that this matches their team's internal experience with the model.
More from Models
- Gemini 4 Neon release sparks debate: is Google ahead on recursive self-improvement? — inductionheads · 2026-11-19
- Gemini Neon test: it names which "AI SEO courses" are rebranded legacy content and which to skip — gaganghotra_ · 2026-11-19
- Gemini 4 Neon's 39% SWE-sweep questioned: results hinge on the harness — OfirPress · 2026-11-19
- scaling01 mocks benchmark tables: leading every eval doesn't mean the better model — scaling01 · 2026-11-19
- Microsoft launches MAI Realtime 1: speech-to-speech voice AI at $0.01 per audio minute — alexcovo_eth · 2026-11-19
- Gemini 4 Neon appears live and quick: researcher shares one-shot demos, best scores 7/10 — SamuelAlbanie · 2026-11-19