Compare models
Up to 4 models side by side.
Provider | Anthropic | OpenAI | |
|---|---|---|---|
Released | Nov 1, 2026seed | Aug 7, 2025seed | Jun 17, 2025seed |
Input price USD per 1M tokens | $4 | $1.25seed | $1.25seed |
Output price USD per 1M tokens | $20 | $10seed | $10seed |
Workload cost Chat reply (2K in, 500 out) | $0.02 | $0.0075seed | $0.0075seed |
Context window | 1M | 400Kseed | 1.05Mseed |
Max output | 128K | 128Kseed | 66Kseed |
Output speed tokens per second | 60seed | 70seed | 90seed |
Time to first token seconds | 2sseed | 4sseed | 3sseed |
GPQA Diamond Graduate-level science questions that resist web search. | 86%seed | 85%seed | 84%seed |
SWE-bench Verified Fixing real GitHub issues in Python repositories. | 81%seed | 74%seed | 63%seed |
MMLU-Pro Broad knowledge and reasoning across 14 subjects. | 87%seed | 86%seed | 86%seed |
AIME Competition math problems. | 92%seed | 94%seed | 86%seed |
Arena Elo Human preference rating from head-to-head chats. | 1505seed | 1460seed | 1455seed |
Inputs | text, image, pdf | text, image | text, image, audio, video, pdf |
Open weights | No | No | No |
Good at | codingagentswritingreasoninglong-context | reasoningcodingagents | long-contextvisionreasoningmultilingual |
Notes | Anthropic's flagship everyday model. Strong at coding, agents and careful writing, at half the price of Fable. | OpenAI's general-purpose reasoning model. Strong at math, coding and tool use. | Google's long-context reasoning model with strong video and document understanding. |
Best value in each row is highlighted. Share this page's URL to share the comparison.