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.
- 🥇
claude-fable-5Anthropic PBC·$10.00 / $50.00 per 1M59.959.9 - 🥈
gpt-5.6-solOpenAI Inc.·$5.00 / $30.00 per 1M58.958.9 - 🥉
kimi-k3Moonshot AI·$3.00 / $15.00 per 1M57.157.1 - 4claude-opus-4-8Anthropic PBC·$5.00 / $25.00 per 1M55.755.7
- 5gpt-5.6-terraOpenAI Inc.·$2.50 / $15.00 per 1M55.055.0
- 6gpt-5.5OpenAI Inc.·$5.00 / $30.00 per 1M54.854.8
- 7grok-4.5xAI Corp.·$2.00 / $6.00 per 1M53.853.8
- 8claude-opus-4-7Anthropic PBC·$5.00 / $25.00 per 1M53.553.5
- 9claude-sonnet-5Anthropic PBC·$2.00 / $10.00 per 1M53.453.4
- 10gpt-5.4OpenAI Inc.·$2.50 / $15.00 per 1M51.451.4
- 11gpt-5.6-lunaOpenAI Inc.·$1.00 / $6.00 per 1M51.251.2
- 12
glm-5.2Z.ai·$1.40 / $4.40 per 1M51.151.1 - 13
gemini-3.5-flashGoogle LLC (Vertex AI)·$1.50 / $9.00 per 1M50.250.2 - 14gemini-3.6-flashGoogle LLC (Vertex AI)·$1.50 / $7.00 per 1M50.150.1
- 15claude-sonnet-4-6Anthropic PBC·$3.00 / $15.00 per 1M47.247.2
- 16
gemini-3.1-pro-previewGoogle LLC (Gemini API)·$2.00 / $12.00 per 1M46.546.5 - 17
qwen3.7-maxAlibaba Cloud·$2.50 / $7.50 per 1M46.046.0 - 18minimax-m3MiniMax·$0.30 / $1.20 per 1M44.444.4
- 19gpt-5.3-codexOpenAI Responses·$1.75 / $14.00 per 1M44.344.3
- 20
deepseek-v4-proDeepSeek·$0.43 / $0.87 per 1M44.344.3 - 21kimi-k2.6Moonshot AI·$0.95 / $4.00 per 1M44.244.2
- 22claude-opus-4-6Anthropic PBC·$5.00 / $25.00 per 1M43.743.7
- 23gpt-5.2OpenAI Inc.·$1.75 / $14.00 per 1M42.242.2
- 24
XiaomiMiMo/MiMo-V2.5-ProDeepInfra Inc.·$1.00 / $3.00 per 1M42.242.2 - 25kimi-k2.7-codeMoonshot AI·$0.95 / $4.00 per 1M41.941.9
- 26
tencent/hy3Novita AI·Free / Free per 1M41.241.2 - 27claude-opus-4-5Anthropic PBC·$5.00 / $25.00 per 1M40.840.8
- 28inklingthinkingmachines·$1.87 / $4.68 per 1M40.740.7
- 29deepseek-v4-flashDeepSeek·$0.14 / $0.28 per 1M40.340.3
- 30glm-5.1Z.ai·$1.40 / $4.40 per 1M40.240.2
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 — 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.