Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

Comparing agents instead? Switch to agent compare →

Selected

GPT-5×

Claude 4.6 Sonnet×

DeepSeek-R1×

Claude 4.7 Opus×Clear all

	GPT-5 OpenAI	Claude 4.6 Sonnet Anthropic	DeepSeek-R1 DeepSeek	Claude 4.7 Opus Anthropic
Vendor	OpenAI	Anthropic	DeepSeek	Anthropic
Family	GPT	Claude	DeepSeek	Claude
Release date	2025-08-07	2026-02-17	2025-01-20	2026-04-16
Context window	400,000 tokens	1,000,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	—	—	671B	—
Modality	text, vision, audio	text, vision	text	text, vision
License	proprietary	proprietary	MIT	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.	Anthropic's mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.	Reasoning-focused open-weight model.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle). Optimized for complex reasoning and coding. Improved software engineering, long-running coding tasks, and higher-resolution vision over Claude 4.6.
Links	vendor →		weights →	vendor →
Benchmarks
MMLU-Pro	85.1%	85.4%	—	88.2%
GPQA-D	87.3%	85.8%	—	90.1%
HumanEval	95.2%	95.9%	—	97.4%
Aider	85.4%	83.6%	—	91.2%
AIME-25	91.0%	87.4%	79.8%	93.5%
LiveCB	74.5%	73.8%	—	80.2%
MMMU	74.1%	—	—	79.0%