Which AI models are strongest right now, as a tier list, plus the best picks for coding, agents, value and speed. It updates itself every day from the Artificial Analysis free API; data © Artificial Analysis, used with attribution.

SSS54+
Claude Opus 5.5 58Anthropic
Claude Sonnet 5.5 56Anthropic
Muse Wonder Full 56Meta
Kimi K3.1 Pro 55Kimi
SS50–53
Claude Fable 5.1 53Anthropic
GPT-6 Astra 53OpenAI
Gemini 4 Argon 53Google
GPT-6.1 Sol 52OpenAI
Muse Wonder 52Meta
S43–49
Grok 4.7 46SpaceXAI
MiMo-V2.6-Pro 46Xiaomi
DeepSeek V4.1 Flash 1017 45DeepSeek
GLM-5.3 45Z AI
Qwen3.8 Max 0902 45Alibaba
Ling 3.1 Flash 1019 44InclusionAI
Step 5 Preview 44StepFun
Claude Haiku 5.5 43Anthropic
MiniMax-M3.1-Flash 43MiniMax
A38–42
GLM-5.3-Flash 42Z AI
GPT-5.6 Terra 42OpenAI
Gemini 3.8 Flash 41Google
Ling 3.1 Flash 41InclusionAI
Qwen3.8 2.4T A95B 40Alibaba
Qwen3.8-Flash-Next 40Alibaba
Muse Spark Open 39Meta
GPT-6 Luna 38OpenAI
MiMo-V2.6-Flash 38Xiaomi
Mistral Large 4 Preview 38Mistral
B30–37
DeepSeek V4 Pro 0813 36DeepSeek
DeepSeek V4 Flash Vision 35DeepSeek
JT-4.1 Flash 236B A21B 34China Mobile
Qwen3.8 27B 34Alibaba
K2 Horizon 375B A23B 31Institute of Foundation Models
Beam 1.0 30Reflection
Gemini 3.1 Pro Preview 30Google
C23–29
MiniMax-M3 29MiniMax
Quasar 438B 27Multiverse Computing
Solar Pro 4 27Upstage
Apodex 1.1 26Apodex
GPT-5.5 Instant 26OpenAI
Inkling Small 26Thinking Machines
Kimi K2.7 Code 26Kimi
Nemotron 3.5 Super VL 26NVIDIA
Hy3 25Tencent
Inkling 25Thinking Machines
K2 Horizon MoVA 36B A4B 25Institute of Foundation Models
Ling-3.0-flash-VL 25InclusionAI
Qwen3.7 Plus 25Alibaba
Solar Mini 4 24Upstage
Ling-3.0-flash-Fin 23InclusionAI
Nemotron 3 Ultra 23NVIDIA

As of 2026-10-25. Source: Artificial Analysis Intelligence Index. Each model family's best variant, tiered by how far it scores below the current leader. Seeded by hand from the public leaderboard on 2026-10-25 (scores marked with an asterisk there are left out). Coding, agent, value and speed rankings appear after the first automatic update.

How to read it

  • The score is the Artificial Analysis Intelligence Index: one number combining about ten hard evaluations (reasoning, knowledge, coding, agentic tasks). Higher is better; the exact version is shown next to the source.
  • Tiers are relative: SSS means within 4 points of the current leader, SS within 8, S within 15, A within 20, B within 28, C within
    1. When a new index version moves every score, the tiers still mean the same thing.
  • One entry per model: many models come in effort levels (low, high, max); each family is shown at its best level.
  • A benchmark is not your use case. A model two tiers lower may be faster, cheaper or better at your specific task: check the category lists, then try it.

Sources