The world's leading AI models, ranked
Aggregated live from Artificial Analysis and OpenRouter. Track every frontier model: intelligence, coding, math, speed and cost, all in one place.
| Rank | Model | |||||||
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 (Max, Default Fallback) Anthropic | 64.6 | 64.6 | 89 | $16 | |||
| 2 | Claude Fable 5.2 (Xhigh, Default Fallback) Anthropic | 62.2 | 62.2 | 85 | $16 | |||
| 3 | GPT-6.2 Astra (Max) OpenAI | 62.1 | 62.1 | 63 | $16 | |||
| 4 | Claude Fable 5.2 (High, Default Fallback) Anthropic | 61.8 | 61.8 | 73 | $16 | |||
| 5 | GPT-6.2 Astra (Xhigh) OpenAI | 61.6 | 61.6 | 44 | $16 | |||
| 6 | Gemini 4 Neon (Xhigh) Google | 61.4 | 61.4 | 110 | $6 | |||
| 7 | Claude Opus 5.5 (Max, Default Fallback) Anthropic | 59.1 | 59.1 | 96 | $8 | |||
| 8 | Gemini 4 Carbon Google🔊📄🖼T🎬 | 58.3 | 58.3 | 82 | $8 | 1.0M | ||
| 9 | Claude Opus 5.5 (Xhigh, Default Fallback) Anthropic | 57.4 | 57.4 | 76 | $8 | |||
| 10 | GPT-6.2 Sol (Max) OpenAI | 57.3 | 57.3 | 77 | $4 |
Frequently asked questions
+ What is the best AI model right now?
By the DataCore composite score (intelligence, coding, math), Claude Fable 5.2 (Max, Default Fallback) currently leads our ranking of 200 AI models from 32 providers, updated continuously.
+ Which AI model is the cheapest?
Gemini 4 Hydrogen (Xhigh) is among the lowest-cost frontier options, around $3 per 1M output tokens. You can sort and filter the leaderboard by price.
+ What is the fastest LLM?
Muse Ember (Max) reaches the highest output speed (~640 tokens/sec). Speed and latency are measured by Artificial Analysis.
+ What is an AI model "time horizon"?
It's METR's metric: the length of task (in human time) a model can complete with a 50% success rate. A longer time horizon means the model can handle longer, more complex agentic tasks.
+ What is the best open-source LLM?
The board tracks 49 open-weight models such as DeepSeek, Qwen, Llama and GLM. Use the "Open weights" filter to compare them head-to-head.
+ Where does the data come from and how often is it updated?
Aggregated from Artificial Analysis (intelligence, coding, math, speed, price), METR (time horizon) and OpenRouter (catalog, live pricing). Data refreshes continuously (≈10-minute cache).
Data sources
Model catalog, context window, modalities, live pricing
Intelligence Index, coding & math scores, speed, latency
50% task-completion time horizon (how long a task a model can finish)
Polyglot code-editing benchmark (pass rate %)