660 models • 553 with benchmarks • 491 with AA Score • Synced: July 17, 2026
What is the best LLM today?
Most Intelligent
AA Score — Artificial Analysis · updated every 6h
Fastest?
Fastest
Output tokens/second · higher is better
Best value for money?
Most Value per Dollar
AA Score per US$ (blended 3:1)
🏆 Ranking por Inteligência
Score AA — Artificial Analysis · top 20
Anthropic
OpenAIOpenAIOpenAIAnthropicOpenAIOpenAI
xaiOpenAIScore AA = AA Intelligence Index da Artificial Analysis. Atualizado a cada 6h. Clique em qualquer modelo para ver benchmarks detalhados.
660
Models
104
Companies
491
With AA Score
105
Reasoning
109
Open Source
155
Multimodal
Ranking by AA Score
Classification based on the AA Intelligence Index by Artificial Analysis — composite score updated every 6 hours.
| # | Modelo | ELO | Input $/1M |
|---|---|---|---|
| 🥇 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic | 1507 | $10.00 |
| · | GPT-5.6 Sol (max)NovoOpenAI | — | $5.00 |
| 🥉 | GPT-5.6 Sol (xhigh)NovoOpenAI | 1486 | $5.00 |
| 4 | Kimi K3Novo Kimi | 1486 | $3.00 |
| · | GPT-5.6 Sol (high)NovoOpenAI | — | $5.00 |
| 6 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic | 1483 | $5.00 |
| · | GPT-5.6 Terra (max)NovoOpenAI | — | $2.50 |
| 8 | GPT-5.5OpenAI | 1482 | $5.00 |
| 9 | Grok 4.5Novoxai | 1465 | $2.00 |
| · | GPT-5.6 Sol (medium)NovoOpenAI | — | $5.00 |
| 11 | Claude Opus 4.7Anthropic | 1503 | $5.00 |
| 12 | Claude Sonnet 5Novoanthropic | 1461 | $2.00 |
| · | GPT-5.6 Terra (xhigh)NovoOpenAI | — | $2.50 |
| 14 | GPT-5.4OpenAI | 1478 | $2.50 |
| · | GPT-5.6 Luna (max)NovoOpenAI | — | $1.00 |
| 16 | GLM-5.2 (max) Z.ai | 1468 | $1.40 |
| 17 | Muse Spark 1.1 (xhigh)Novo Meta | 1493 | $1.25 |
| · | GPT-5.5 ProOpenAI | — | — |
| 19 | Gemini 3.5 Flash Google | 1476 | $1.50 |
| · | GPT-5.6 Sol (low)NovoOpenAI | — | $5.00 |
Preços em USD por 1M tokens de input. Estimativa em BRL: câmbio de mercado + IOF de 6,38%. Consulte metodologia para detalhes.
OS = Open Source • MM = Multimodal • R = Reasoning •AA Score: Artificial Analysis • Intel.: Artificial Analysis •Pricing: OpenRouter •View full methodology
⚡ Velocidade de Inferência
Tokens por segundo — top 15
NVIDIAVelocidade em tokens/segundo medida via API. TTFT = Time to First Token (latência até a primeira resposta).
Models by Company
AI Benchmark Guide 2026
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) is the most intelligent AI model in 2026 with an AA Score of 59.9, according to the AA Intelligence Index by Artificial Analysis — a composite score updated every 6 hours. The language model (LLM) market in 2026 is dominated by a race between OpenAI, Anthropic, Google DeepMind, Meta AI and labs like DeepSeek, Alibaba (Qwen) and xAI (Grok). With over 660 models available via API, choosing the right model for each use case has become a complex decision involving quality (measured by benchmarks like AA Intelligence Index, MMLU and SWE-bench), token pricing, inference speed, context and multimodal capabilities.
AA Score — Artificial Analysis Intelligence Index↓
Intelligence Index (Artificial Analysis)↓
Pricing and Value↓
Context Window: Why It Matters↓
Open Source vs Proprietary↓
Frequently Asked Questions
What is the best AI model in 2026?↓
According to the AA Intelligence Index by Artificial Analysis, Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) leads with a Score of 59.9. However, "best" depends on use case: for value, Qwen3.5 4B (Reasoning) offers excellent quality at low cost.
What is the AA Score?↓
The AA Score is the Intelligence Index by Artificial Analysis — a composite score (0-100) combining multiple reasoning, code, math and science benchmarks. It is automatically updated every 6 hours from the public Artificial Analysis API.
What is the cheapest AI model?↓
Among models with good quality (AA Score > 40), Hy3-preview (Reasoning) is the most affordable at $0.12/1M input tokens.
Are benchmarks reliable?↓
Benchmarks are indicative, not definitive. The AA Intelligence Index is considered robust because it combines multiple standardized evaluations. Individual benchmarks (MMLU, GPQA) can suffer from contamination. We recommend testing on your specific use case.
ChatGPT vs Claude vs Gemini — which is better?↓
ChatGPT (OpenAI) is the most popular and versatile. Claude (Anthropic) excels at long reasoning and quality text. Gemini (Google) integrates well with the Google ecosystem. The ideal choice depends on your use case — use our comparator at /benchmark/comparar.