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-opus-5-5Anthropic路$4.00 / $20.00 per 1M57.657.6 - 馃claude-sonnet-5-5Anthropic路$2.00 / $10.00 per 1M56.056.0
- 馃claude-fable-5.1Anthropic路$10.00 / $50.00 per 1M53.453.4
- 4
gpt-6-astraOpenAI路$10.00 / $50.00 per 1M52.752.7 - 5
gemini-4-argon50% offGoogle Vertex AI路$2.00 / $10.00 per 1M52.652.6 - 6gpt-6.1-solOpenAI路$2.00 / $10.00 per 1M51.851.8
- 7claude-opus-5Anthropic路$5.00 / $25.00 per 1M50.850.8
- 8claude-fable-5Anthropic路$10.00 / $50.00 per 1M49.649.6
- 9muse-spark-1.3meta路$1.25 / $4.25 per 1M48.148.1
- 10gpt-6-solOpenAI路$2.00 / $10.00 per 1M47.647.6
- 11gpt-5.6-solOpenAI路$4.00 / $20.00 per 1M47.047.0
- 12grok-4.7xAI路$2.00 / $6.00 per 1M46.446.4
- 13
mimo-v2.6-proDeepInfra路$0.43 / $0.87 per 1M46.346.3 - 14
qwen3.8-maxAlibaba Cloud路$2.00 / $6.00 per 1M45.445.4 - 15
deepseek-v4.1-flash-1017DeepSeek路$0.30 / $1.20 per 1M45.145.1 - 16
glm-5.3Z.ai路$1.40 / $4.40 per 1M44.844.8 - 17grok-4.6xAI路$2.00 / $6.00 per 1M44.344.3
- 18step-5-previewDeepInfra路$1.00 / $2.70 per 1M43.743.7
- 19
kimi-k3Moonshot AI路$3.00 / $15.00 per 1M43.643.6 - 20claude-haiku-5-5Anthropic路$0.10 / $0.50 per 1M43.443.4
- 21minimax-m3.1-flashMiniMax路$0.15 / $0.60 per 1M42.742.7
- 22gpt-5.6-terraOpenAI路$2.00 / $12.00 per 1M42.142.1
- 23glm-5.3-flashZ.ai路$0.15 / $0.50 per 1M41.841.8
- 24claude-opus-4-8Anthropic路$5.00 / $25.00 per 1M41.841.8
- 25
ling-3.1-flashNovita AI路Free / Free per 1M41.141.1 - 26gemini-3.8-flash50% offGoogle Vertex AI路$0.75 / $3.75 per 1M40.940.9
- 27claude-opus-4-7Anthropic路$5.00 / $25.00 per 1M40.740.7
- 28qwen3.8-2.4t-a95bTensorX路$2.50 / $6.00 per 1M39.939.9
- 29qwen3.8-flash-nextTensorX路$0.20 / $0.50 per 1M39.839.8
- 30gemini-3.7-flash50% offGoogle Vertex AI路$0.75 / $3.75 per 1M39.639.6
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.