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-5.2Anthropic路$8.00 / $40.00 per 1M64.664.6 - 馃
gemini-4-carbon50% offGoogle Vertex AI路$2.00 / $10.00 per 1M60.060.0 - 馃claude-opus-5-5Anthropic路$4.00 / $20.00 per 1M59.159.1
- 4
gpt-6-astraOpenAI路$10.00 / $50.00 per 1M56.956.9 - 5gpt-6.1-solOpenAI路$2.00 / $10.00 per 1M54.654.6
- 6claude-sonnet-5-5Anthropic路$2.00 / $10.00 per 1M54.554.5
- 7gpt-6.1-terraOpenAI路$1.00 / $5.00 per 1M51.351.3
- 8gemini-4-argon50% offGoogle Vertex AI路$2.00 / $10.00 per 1M50.450.4
- 9claude-fable-5.1Anthropic路$10.00 / $50.00 per 1M50.050.0
- 10
kimi-k3.1-proMoonshot AI路$2.00 / $10.00 per 1M46.546.5 - 11gpt-6-solOpenAI路$2.00 / $10.00 per 1M44.244.2
- 12claude-opus-5Anthropic路$5.00 / $25.00 per 1M44.244.2
- 13muse-spark-1.3meta路$1.25 / $4.25 per 1M36.636.6
- 14claude-haiku-5-5Anthropic路$0.10 / $0.50 per 1M36.536.5
- 15grok-4.7xAI路$2.00 / $6.00 per 1M35.535.5
- 16hy4-previewTencent路$0.83 / $2.50 per 1M34.634.6
- 17
qwen3.8-maxAlibaba Cloud路$2.00 / $6.00 per 1M33.733.7 - 18
deepseek-v4.1-flash-1017DeepSeek路$0.30 / $1.20 per 1M32.632.6 - 19gpt-5.6-terraOpenAI路$2.00 / $12.00 per 1M32.332.3
- 20
glm-5.3Z.ai路$1.40 / $4.40 per 1M31.731.7 - 21grok-4.6xAI路$2.00 / $6.00 per 1M31.031.0
- 22gemini-3.8-flash50% offGoogle Vertex AI路$0.75 / $3.75 per 1M30.830.8
- 23
mimo-v2.6-proDeepInfra路$0.43 / $0.87 per 1M29.929.9 - 24minimax-m3.1-flashMiniMax路$0.15 / $0.60 per 1M29.129.1
- 25step-5-previewDeepInfra路$1.00 / $2.70 per 1M28.528.5
- 26gpt-6-lunaOpenAI路$0.10 / $0.50 per 1M27.927.9
- 27glm-5.3-flashZ.ai路$0.15 / $0.50 per 1M27.827.8
- 28mimo-v2.6-flashDeepInfra路$0.14 / $0.28 per 1M26.726.7
- 29
mistral-large-450% offMistral AI路$0.68 / $2.09 per 1M26.126.1 - 30
muse-spark-openTogether AI路$1.25 / $4.25 per 1M24.924.9
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.