AI Leaderboard — Rankings for 300+ Top AI Models by Intelligence, Speed & Price

Name: LLM Stats Leaderboard — AI Models with Live Pricing & Benchmarks
Creator: LLM Stats
License: https://llm-stats.com/legal/terms-of-service

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 Astra

96.0%gpqa

wins at coding

Claude Opus 5

27arena

cheapest in the top 10

Gemini 3.1 Pro

$2.00/M tok

fastest output

Gemini 3.7 Flash

410tok/s

longest context window

Grok-4 Fast Reasoning

2.0M tokenstokens

best open-weights

Kimi K3

93.5%gpqa

Full leaderboardFull

418

									License
1	Claude Opus 5.5– Anthropic	60.4	59.5	49.9	45.5	1.0M	293c/s	$4.76	Proprietary
2	Claude Sonnet 5.5– Anthropic	58.4	57.2	47.6	43.3	1.0M	—	$2.38	Proprietary
3	GPT-6 Astra– OpenAI	58.2	57.3	46.4	45.0	1.1M	—	$11.90	Proprietary
4	Gemini 4 Argon– Google	55.1	53.2	42.5	41.2	1.0M	—	$2.38	Proprietary
5	Claude Mythos Preview–UNRELEASED Anthropic	54.5	55.6	43.8	36.6	—	—	—	Proprietary
6	Claude Opus 51 Anthropic	53.8	54.1	38.4	38.3	1.0M	—	$5.95	Proprietary
7	GPT-6.1 Sol1 OpenAI	53.6	51.6	38.6	37.9	1.1M	—	$2.38	Proprietary
8	GPT-5.6 Sol1 OpenAI	53.3	52.7	42.5	39.1	1.1M	91c/s	$6.19	Proprietary
9	Claude Fable 5.11 Anthropic	53.2	50.8	34.3	38.2	1.0M	—	$11.90	Proprietary
10	Muse Wonder Full–NEW Meta	53.2	45.7	42.5	41.0	—	—	—	Proprietary
11	Claude Fable 52 Anthropic	53.1	51.2	42.9	38.6	1.0M	—	$11.90	Proprietary
12	Muse Wonder Full–NEW Meta	52.6	41.2	41.4	40.6	—	—	—	Proprietary
13	Muse Spark 1.33 Meta	52.2	51.1	37.9	37.7	1.0M	—	$1.39	Proprietary
14	Kimi K33 Moonshot AI	51.9	51.3	40.0	37.3	1.0M	—	$3.39	Open Source
15	DeepSeek-V4.1-Flash-1017–NEW DeepSeek	51.2	48.8	39.3	38.7	1.0M	—	$0.34	Open Source

1-15 of 418

Recent

New Models

Announced in the last 15 days.

All updates

Index

Performance Index

Composite TrueSkill ratings across published benchmarks.

Full leaderboard

FAQ

Quick answers for choosing, comparing and interpreting today's leading AI models.

Which AI model ranks #1 on the LLM Leaderboard?

On the LLM Stats Leaderboard, GPT-6 Astra currently leads on GPQA Diamond (96.0% gpqa), the most discriminating reasoning benchmark at the frontier. This AI leaderboard ranks models by the LLM Stats Score, which aggregates GPQA, SWE-Bench Verified, coding-arena performance and pricing into one comparable AI ranking. Rankings refresh continuously as new benchmark results land.

What is the best AI model right now?

"Best" depends on what you're optimizing for. For frontier reasoning, GPT-6 Astra leads on GPQA. For coding agents, Claude Opus 5 is the strongest in head-to-head coding-arena play. For low cost at frontier quality, Gemini 3.1 Pro is the cheapest in the top 10 at $2.00 /M tok. The leaders summary above the table names the current winner per axis.

What are the best LLMs in 2026?

The leading LLMs in 2026 are GPT-6 Astra, Claude Opus 5, and the frontier models from OpenAI (GPT-5 family), Anthropic (Claude Opus and Sonnet), Google (Gemini 3 Pro), xAI (Grok 4), DeepSeek (V3 / R1) and Z.AI (GLM-5). Open-weights leaders include Llama, Qwen and DeepSeek. The full ranking is in the leaderboard table above.

What is the cheapest AI model in the top 10?

Gemini 3.1 Pro is the cheapest model in the top 10 by GPQA Diamond, at $2.00 /M tok input. The Cheapest filter on the leaderboard restricts to verified, currently-available frontier models — pricing is pulled from each provider's public price list and cross-checked against billing samples through the LLM Stats proxy.

Which AI model has the largest context window?

Grok-4 Fast Reasoning currently exposes the largest practical context window at 2.0M tokens tokens. Larger context lets you keep more documents, conversation history and tool traces in a single request. For long-document workloads, also consult the per-model "effective context" notes on each model detail page — providers vary in how well they actually use the upper end of their advertised windows.

What is the fastest LLM by output speed?

Gemini 3.7 Flash currently has the highest output throughput at 410 tok/s. Output speed is measured consistently across supported provider APIs and summarized over a recent observation window. Fast inference matters most for streaming chat UIs and agentic loops; for batched async workloads, blended price per 1M tokens is usually the better axis.

Which is the best open-source AI model?

Kimi K3 currently leads among open-weights LLMs (93.5% gpqa). The open-weights ecosystem is dominated by Llama, Qwen, DeepSeek, Mistral, GLM and Gemma. The dedicated Open LLM Leaderboard filters this catalog to models with publicly released weights so you can self-host or fine-tune.

How is the LLM Stats Score calculated?

The LLM Stats Score combines several categories of model evidence into one comparable number using an uncertainty-aware approach. See the LLM Stats Score methodology for a high-level overview, limitations, and contact information for further details. 418 canonical models are tracked across every major lab and inference provider.