SmophyAI

Published daily · Next update 02:00 UTC

Trends · July 5, 2026 - November 6, 2026

Which AI models are climbing or falling

Climbing

ModelStart → peak rankShare Δ

Declining

ModelStart → worst rankShare Δ
MiniMax: MiniMax M3 (batch)#3 → #42-8.7pts
Anthropic: Claude Sonnet 5 (batch)#15 → #43-1.2pts
Z.ai: GLM 5.2#4 → #30-5.9pts
NVIDIA: Nemotron 3 Ultra (free)#10 → #34-1.1pts
Google: Gemma 4 26B A4B (free)#24 → #47-0.6pts
Google: Gemini 3 Flash Preview (batch)#13 → #36-1.6pts
OpenAI: gpt-oss-120b (batch)#22 → #43-0.8pts
Google: Gemini 3.1 Flash Lite (batch)#23 → #43-0.7pts

Computed from real daily usage history (July 5, 2026 to November 6, 2026). This page deepens automatically as more history accumulates, with no manual update required.

Source: OpenRouter (openrouter.ai/rankings), as of November 7, 2026.

Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Methodology: www.smophy.ai/benchmark/methodology

Token counts originate from each provider's own tokenizer and are not directly comparable across providers.