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-fable-5
Anthropic · Proprietary
1563
$40/M
claude-opus-4-7-thinking
1553
$20/M
claude-sonnet-4-6
1527
$12/M
qwen3.7-max-preview
Alibaba · Proprietary
1526
$3.13/M
mimo-v2.5-pro
Xiaomi · MIT
1520
$0.76/M
gemma-4-31b
Google · Apache 2.0
1497
$0.34/M
mimo-v2.5
1491
$0.24/M
deepseek-v4-flash
DeepSeek · MIT
1480
$0.16/M
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1440
gpt-oss-120b
OpenAI · Apache 2.0
1391
$0.12/M
gpt-oss-20b
1370
$0.11/M
granite-4.1-8b
IBM · Apache 2.0
1352
$0.09/M
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1312
$0.07/M
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1260
$0.03/M