Artificial Analysis benchmarks Gemini 4 Neon across four effort tiers, revamps agentic metrics
ArtificialAnlys · x · 2026-11-19
Artificial Analysis has evaluated Gemini 4 Neon across four effort tiers (Low/Medium/High/Xhigh) on its Intelligence Index v5, adding the model to its comparison platform.
Other notable updates from the benchmarking site:
- New evaluations including GPT-6.2 Astra and Sol, putting OpenAI at #2 on the Intelligence Index with the GPT-6.2 lineup
- API Performance Benchmarking v3 now uses time per task as its headline metric, with agentic workloads added
- Decision Index v2.1 introduces private benchmarks and scoring that rewards calibrated confidence
- New Optima custom benchmark builder and a model recommender optimizing across intelligence, speed, and cost
Related event: Artificial Analysis Rolls Out Intelligence Index v5(3 posts)→
More from Models
- Cloudflare open-weights Clairic: 27B and 9B models built for extraction — michellechen · 2026-11-19
- Cloudflare open-weights redesigned Clairic 27B and Clairic-flash 9B extraction models — michellechen · 2026-11-19
- ApprenticeBench: closed vs open-weight LLM gap widens to 55 points — ysu_nlp · 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