View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.
Model performance at each price point
Top performers for their cost
claude-opus-4-6-thinking
Anthropic · Proprietary
1495
$20/M
gemini-3-pro
Google · Proprietary
1485
$9.50/M
gemini-3.5-flash
Google · Proprietary
1464
$7.13/M
gemini-3-flash
Google · Proprietary
1459
$2.38/M
deepseek-v4-pro
DeepSeek · MIT
1440
$0.76/M
gemma-4-31b
Google · Apache 2.0
1422
$0.34/M
deepseek-v4-flash-thinking
DeepSeek · MIT
1403
$0.18/M
gemma-3-27b-it
Google · Gemma
1348
$0.14/M
gemma-3-12b-it
Google · Gemma
1334
$0.11/M
gemma-3n-e4b-it
Google · Gemma
1300
$0.10/M
gemma-2-9b-it-simpo
Princeton · MIT
1283
$0.08/M
gemma-3-4b-it
Google · Gemma
1276
$0.07/M
llama-3-8b-instruct
Meta · Llama 3 Community
1196
$0.04/M