AI Leaderboard — Rankings for 300+ Top AI Models by Intelligence, Speed & Price
Independent rankings of GPT, Claude, Gemini, Llama, DeepSeek and 300+ AI models — composite LLM Stats Score, updated continuously from public benchmarks and live API metrics. See the full LLM Leaderboard for complete LLM rankings with advanced filters.
leads on reasoning
GPT-6.2 Astra
97.0%gpqa
wins at coding
Claude Opus 5
27arena
cheapest in the top 10
GPT-6.2 Sol
$2.00/M tok
fastest output
MiniMax M3.1 Flash
344tok/s
longest context window
Grok-4 Fast Reasoning
2.0M tokenstokens
best open-weights
Kimi K3.1 Pro
94.2%gpqa
| License | |||||||||
|---|---|---|---|---|---|---|---|---|---|
1 | Anthropic | 60.6 | 59.8 | 49.9 | 46.5 | 1.0M | — | $9.52 | Proprietary |
2 | Anthropic | 58.5 | 52.5 | 43.4 | 43.8 | 1.0M | — | $9.52 | Proprietary |
3 | OpenAI | 58.0 | 55.1 | 47.4 | 44.9 | 1.1M | — | $9.52 | Proprietary |
4 | Anthropic | 58.0 | 56.9 | 47.5 | 43.5 | 1.0M | — | $4.76 | Proprietary |
5 | Google | 56.6 | 53.1 | 45.0 | 43.3 | 1.0M | 88c/s | $2.38 | Proprietary |
6 | Anthropic | 56.3 | 54.9 | 45.7 | 41.7 | 1.0M | — | $2.38 | Proprietary |
7 | OpenAI | 55.4 | 54.2 | 43.1 | 41.9 | 1.1M | 87c/s | $11.90 | Proprietary |
8 | OpenAI | 53.9 | 49.6 | 42.6 | 40.3 | 1.1M | — | $2.38 | Proprietary |
9 | Moonshot AI | 53.9 | 52.9 | 40.4 | 39.8 | 1.0M | 142c/s | $2.38 | Open Source |
10 | Anthropic | 53.2 | 54.2 | 42.5 | 35.0 | — | — | — | Proprietary |
11 | Google | 52.9 | 50.6 | 40.9 | 39.4 | 1.0M | 158c/s | $2.38 | Proprietary |
12 | Meta | 52.1 | 44.5 | 41.9 | 40.3 | — | — | — | Proprietary |
13 | Anthropic | 52.1 | 52.1 | 37.3 | 36.7 | 1.0M | — | $5.95 | Proprietary |
14 | OpenAI | 51.8 | 49.2 | 37.2 | 35.9 | 1.1M | — | $2.38 | Proprietary |
15 | Anthropic | 51.6 | 49.3 | 33.9 | 36.9 | 1.0M | — | $11.90 | Proprietary |
New Models
Announced in the last 15 days.
Performance Index
Composite TrueSkill ratings across published benchmarks.
FAQ
Quick answers for choosing, comparing and interpreting today's leading AI models.