Efficiency Frontier

> 0 models · scroll to zoom, drag to pan, click a bubble to open.

OPENAI
ANTHROPIC
GOOGLE
DEEPSEEK
QWEN
KIMI
META
XAI
MISTRAL
1.0×
PERFORMANCE — INTELLIGENCE INDEX (0-100) →← OUTPUT COST ($ / 1M TOKENS) [log]

> Performance = composite intelligence index (0-100) derived from public benchmark aggregates (MMLU-Pro, GPQA, MATH, HumanEval, SWE-bench, Artificial Analysis). Lower-left is the frontier: high score, low $/1M output tokens. 0 models hidden — no public benchmark match.