Agentic AI Benchmarks

Interactive cost-vs-performance comparisons of frontier AI models. Automatically synced from Artificial Analysis.

Cost vs. Overall Intelligence

Blended price per 1M tokens vs. Overall Intelligence

Most Attractive

High overall intelligence, low cost

Expensive

High overall intelligence, high cost

Budget

Low overall intelligence, low cost

Avoid

Low overall intelligence, high cost

Click any point to open the model page on Artificial Analysis.

84 of 84 active
·

Recent Releases

DeepSeek V4.1 Flash (max)
DeepSeek · Sep 10, 2026
GPT-6 Astra (max)
OpenAI · Sep 3, 2026
GPT-6 Astra (xhigh)
OpenAI · Sep 3, 2026
GPT-6 Astra (high)
OpenAI · Sep 3, 2026
GPT-6 Astra (medium)
OpenAI · Sep 3, 2026
GPT-6 Astra (low)
OpenAI · Sep 3, 2026
Muse Spark 1.3 (max)
Meta · Sep 2, 2026
Muse Spark 1.3 (xhigh)
Meta · Sep 2, 2026
Gemini 3.8 Flash (high)
Google · Sep 2, 2026
Gemini 3.8 Flash (medium)
Google · Sep 2, 2026
Gemini 3.8 Flash (low)
Google · Sep 2, 2026
Claude Fable 5.1 (max with fallback)
Anthropic · Sep 1, 2026
Claude Fable 5.1 (xhigh with fallback)
Anthropic · Sep 1, 2026
Claude Fable 5.1 (medium with fallback)
Anthropic · Sep 1, 2026
GLM-5.3-Flash
Z AI · Aug 26, 2026
DeepSeek V4 Flash Vision (max)
DeepSeek · Aug 21, 2026
GLM-5.3 (max)
Z AI · Aug 18, 2026
Qwen3.8 27B (xhigh)
Alibaba · Aug 14, 2026
Gemini 3.7 Flash (medium)
Google · Aug 13, 2026
Gemini 3.7 Flash (high)
Google · Aug 13, 2026
Gemini 3.7 Flash (low)
Google · Aug 13, 2026
DeepSeek V4 Pro 0813 (max)
DeepSeek · Aug 13, 2026
Grok 4.6 (high)
SpaceXAI · Aug 12, 2026
Qwen3.8 2.4T A95B
Alibaba · Aug 12, 2026
Muse Spark 1.2 (xhigh)
Meta · Aug 5, 2026
Qwen3.8 Max
Alibaba · Aug 3, 2026
DeepSeek V4 Flash 0731 (max)
DeepSeek · Jul 31, 2026
Claude Opus 5 (max)
Anthropic · Jul 24, 2026
Gemini 3.6 Flash
Google · Jul 21, 2026
Kimi K3 (max)
Kimi · Jul 16, 2026
GPT-5.6 Sol (max)
OpenAI · Jul 9, 2026
GPT-5.6 Sol (xhigh)
OpenAI · Jul 9, 2026
GPT-5.6 Sol (high)
OpenAI · Jul 9, 2026
GPT-5.6 Terra (max)
OpenAI · Jul 9, 2026
GPT-5.6 Sol (medium)
OpenAI · Jul 9, 2026
GPT-5.6 Terra (xhigh)
OpenAI · Jul 9, 2026
GPT-5.6 Luna (max)
OpenAI · Jul 9, 2026
GPT-5.6 Luna (xhigh)
OpenAI · Jul 9, 2026
GPT-5.6 Terra (high)
OpenAI · Jul 9, 2026
GPT-5.6 Sol (low)
OpenAI · Jul 9, 2026
GPT-5.6 Luna (high)
OpenAI · Jul 9, 2026
GPT-5.6 Terra (medium)
OpenAI · Jul 9, 2026
GPT-5.6 Sol (Non-reasoning)
OpenAI · Jul 9, 2026
GPT-5.6 Terra (low)
OpenAI · Jul 9, 2026
GPT-5.6 Luna (medium)
OpenAI · Jul 9, 2026
GPT-5.6 Terra (Non-reasoning)
OpenAI · Jul 9, 2026
GPT-5.6 Luna (low)
OpenAI · Jul 9, 2026
GPT-5.6 Luna (Non-reasoning)
OpenAI · Jul 9, 2026
Grok 4.5 (high)
SpaceXAI · Jul 8, 2026
Hy3
Tencent · Jul 6, 2026
Claude Sonnet 5 (max)
Anthropic · Jun 30, 2026
GLM-5.2 (max)
Z AI · Jun 16, 2026

Data sourced from Artificial Analysis. Last updated: September 11, 2026.

Prices shown are per 1M tokens. Cost to Run is the total expense to evaluate the model on the Artificial Analysis Intelligence Index.