Smartest AI models
The Artificial Analysis Intelligence Index combines many independent evaluations (reasoning, coding, math, science, agentic tool use) into a single capability score. It is the best at-a-glance signal for raw model intelligence, but always validate on your own workload, since the best model for a specific task is often not the highest overall.
- 馃
claude-fable-5.1Anthropic PBC路$10.00 / $50.00 per 1M65.765.7 - 馃claude-opus-5Anthropic PBC路$5.00 / $25.00 per 1M63.163.1
- 馃claude-fable-5Anthropic PBC路$10.00 / $50.00 per 1M62.162.1
- 4
gpt-6-astraOpenAI Inc.路$10.00 / $50.00 per 1M61.261.2 - 5gpt-5.6-solOpenAI Inc.路$4.00 / $20.00 per 1M60.960.9
- 6grok-4.6xAI Corp.路$2.00 / $6.00 per 1M60.960.9
- 7
kimi-k3Moonshot AI路$3.00 / $15.00 per 1M59.759.7 - 8
glm-5.3Z.ai路$1.40 / $4.40 per 1M59.559.5 - 9
gemini-3.8-flash50% offGoogle LLC (Vertex AI)路$0.75 / $3.75 per 1M58.758.7 - 10
qwen3.8-maxAlibaba Cloud路$2.00 / $6.00 per 1M58.158.1 - 11qwen3.8-2.4t-a95bTensorX Ltd.路$2.50 / $6.00 per 1M57.757.7
- 12glm-5.3-flash50% off until 9 Sep 2026Z.ai路$0.07 / $0.25 per 1M57.557.5
- 13claude-opus-4-8Anthropic PBC路$5.00 / $25.00 per 1M57.357.3
- 14gpt-5.6-terraOpenAI Inc.路$2.00 / $12.00 per 1M56.656.6
- 15gpt-5.5OpenAI Inc.路$5.00 / $30.00 per 1M56.356.3
- 16gemini-3.7-flash@eu50% offGoogle LLC (Vertex AI)路$0.83 / $4.13 per 1M56.056.0
- 17grok-4.5xAI Corp.路$2.00 / $6.00 per 1M55.855.8
- 18qwen3.8-flash-nextTensorX Ltd.路$0.20 / $0.50 per 1M55.855.8
- 19claude-sonnet-5Anthropic PBC路$2.00 / $10.00 per 1M55.355.3
- 20claude-opus-4-7Anthropic PBC路$5.00 / $25.00 per 1M55.055.0
- 21
deepseek-v4-pro-0813DeepSeek路$1.32 / $3.96 per 1M53.253.2 - 22gpt-5.4OpenAI Inc.路$2.50 / $15.00 per 1M53.153.1
- 23glm-5.2Z.ai路$1.40 / $4.40 per 1M52.652.6
- 24gpt-5.6-lunaOpenAI Inc.路$0.20 / $1.20 per 1M52.352.3
- 25
gemini-3.5-flashGoogle LLC (Gemini API)路$1.50 / $9.00 per 1M52.052.0 - 26deepseek-v4-flash-0731DeepSeek路$0.44 / $1.32 per 1M51.851.8
- 27gemini-3.6-flashGoogle LLC (Gemini API)路$1.50 / $7.00 per 1M51.651.6
- 28claude-sonnet-4-6Anthropic PBC路$3.00 / $15.00 per 1M48.448.4
- 29gemini-3.1-pro-previewGoogle LLC (Gemini API)路$2.00 / $12.00 per 1M47.747.7
- 30qwen3.7-maxAlibaba Cloud路$2.50 / $7.50 per 1M46.746.7
Explore other rankings
How we rank
Scores for Intelligence Index come from Artificial Analysis, an independent AI benchmarking service. When a model is available through multiple providers (e.g. Anthropic direct, AWS Bedrock, Google Vertex), we show one canonical entry per model family so the ranking isn't polluted by duplicates. Benchmarks measure specific skills, so always validate on your own workload before committing.
One API for every model on this list
Requesty is OpenAI-compatible and routes to 600+ models. Switch between any of the models above by changing one parameter in your code.