LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS

Leaderboards

Data from Artificial Analysis · Intelligence Index v? · 0 models with data

Value frontier →

Artificial Analysis Intelligence Index. Score uses the “representative tier” (highest-scoring reasoning tier per model).

Leaders of every board

The top 8 on each board, with the metric that ranks them. Open any model for its full pricing across providers.

Intelligence

  • Claude Opus 5.5AA 57.6
  • Claude Sonnet 5.5AA 56
  • Claude Fable 5.1AA 53.4
  • GPT-6 AstraAA 52.7
  • GPT-6.1 SolAA 51.8
  • Claude Opus 5AA 50.8
  • Claude Fable 5AA 49.6
  • Muse Spark 1.3AA 48.1

Coding

  • Claude Fable 5.181.6
  • Claude Opus 578
  • GPT-5.6 Sol77.4
  • GPT-6 Astra76.9
  • Grok 4.676.8
  • GPT-5.6 Terra76.7
  • Claude Fable 576.5
  • Gemini 3.8 Flash76.3

Agentic

  • Claude Fable 5.157.9
  • Claude Opus 556.5
  • Qwen3.8 Max56
  • Muse Spark 1.355.5
  • Qwen3.8 Flash Next53.6
  • GLM-5.353.1
  • Grok 4.653
  • GPT-6 Astra51

Value

  • Ling 3.0 Flash638
  • DeepSeek V4 Flash 0731381
  • Qwen3.8 Flash Next318
  • MiMo-V2.6-Flash276
  • GLM-5.3-Flash257
  • DeepSeek V4.1 Flash226
  • Ling 3.0 Flash VL221
  • Ling 3.0 Flash Fin203

Cost per task

  • Ministral 3 3B$0.0078
  • Ministral 3 8B$0.011
  • Mistral Small 4$0.015
  • nvidia-nemotron-3-nano-30b-a3b$0.017
  • Ministral 3 14B$0.019
  • Granite 4.2 8B$0.024
  • Mistral Large 3$0.031
  • Mistral Small 3.1$0.035

Speed

  • Celeris 11767 tok/s
  • Mercury 2739 tok/s
  • Mercury 2.5661 tok/s
  • Gemini 2.5 Flash-Lite358 tok/s
  • Ling 3.0 Flash347 tok/s
  • Trinity Large Thinking342 tok/s
  • Ling 3.0 Flash Fin338 tok/s
  • Gemini 3.5 Flash Lite335 tok/s

Usage

  • DeepSeek V4.1 Flash65891487.6M
  • GLM-5.3-Flash54949891.7M
  • Space Bunny Alpha52519697.21M
  • Hy4 preview49294711.59M
  • GPT-5.6 Luna45645078.06M
  • DeepSeek V4 Flash 073139154880.07M
  • Nemotron 3 Ultra (free)20450891.31M
  • DeepSeek V4 Flash 042316003722.78M

GPQA Diamond

  • GPT-6 Astra96.1%
  • Gemini 3.8 Flash95.3%
  • Grok 4.694.9%
  • GPT-5.6 Sol94.1%
  • Gemini 3.1 Pro Preview94.1%
  • Claude Fable 5.193.7%
  • Kimi K393.5%
  • GPT-5.593.5%

Reading the leaderboards

Each board ranks the same catalog on a different axis: raw intelligence, coding and agentic scores from Artificial Analysis, output speed, cost per task, real 30-day usage, and value. The value board divides intelligence by blended price, with an intelligence floor so a cheap but weak model cannot top it on price alone.

The price basis is switchable because the lowest channel is almost always a third-party gateway, while the official list price reflects the first-party rate. Cost per task can reorder the ranking sharply: a reasoning model with a low unit price still runs up a high bill when it emits many thinking tokens per answer.