Every model, price and benchmark in one place.
A plain-English index of 600 AI models across 40 providers. Compare context windows, token prices and 12 benchmarks without the launch-day noise.
Start here
Pick a path through the index.
All AI models
600 models with prices, context windows and benchmark scores.
Head-to-headCompare two models
1,000 side-by-side comparisons on price, context and benchmarks.
LeaderboardsBenchmark rankings
12 leaderboards covering knowledge, coding, reasoning, safety and preference.
DataCheapest LLM APIs
The lowest token prices in the index, ranked by blended cost.
DataBest open-weight models
The strongest models you can download and self-host.
GuideChoose an LLM for coding
A practical shortlist process for coding assistants and code review.
ReferenceAI glossary
500 terms from attention and KV cache to RAG and RLHF.
DirectoryAI tools
200 chat, coding, image, video and infrastructure tools.
Benchmark leaders
Highest average across scored benchmarks.
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 2 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 3 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 4 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 5 | Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
| 6 | GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| 7 | GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| 8 | Gemini 3 Pro Max | Google DeepMind | 2000000 | $20.57 | 87.9 |
Cheapest capable models
Lowest blended input/output price.
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| SmolLM3 1.5B | Hugging Face | 8192 | $0.04 | 36.8 |
| GPT-NeoX 1.5B | EleutherAI | 32768 | $0.06 | 36.4 |
| Pythia 7B | EleutherAI | 8192 | $0.10 | 40.7 |
| Nemotron Nano 1.5B | NVIDIA | 8192 | $0.10 | 41.5 |
| Zephyr 1.5B | Hugging Face | 32768 | $0.10 | 38.0 |
| Pythia 1.5B | EleutherAI | 4096 | $0.10 | 35.8 |
Largest context windows
Room for long documents and agent traces.
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
| GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| Gemini 3 Pro Max | Google DeepMind | 2000000 | $20.57 | 87.9 |
| Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
Latest data stories
What the index says about price, context and capability.
New guides
Questions
What is the AI & LLM Index?
The AI & LLM Index is an independent reference site that puts AI model prices, context windows and benchmark scores on the same page. It covers 600 models from 40 providers and 12 benchmarks.
Are the benchmark scores official?
No. Scores in this index are modelled estimates generated for comparison at scale. They are not official vendor results or leaderboard submissions. Treat them as relative signals and verify important claims with primary sources.
How are prices listed?
Prices are in US dollars per one million tokens. Input, output and cached input prices are shown separately. A blended 3:1 input-to-output figure is included as a rough planning number.
How often is the index updated?
The demo dataset was generated on 2026-11-09. Model prices and benchmark results change frequently, so check the provider's own documentation before committing to a budget.
Can I compare two specific models?
Yes. The comparison section has 1,000 head-to-head pages. Each one shows specification differences, benchmark wins, price differences and a plain-language verdict.