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×

DeepSeek-R1×

Claude 4.7 Opus×

Gemini 3 Pro×Clear all

	GPT-5 OpenAI	DeepSeek-R1 DeepSeek	Claude 4.7 Opus Anthropic	Gemini 3 Pro Google
Vendor	OpenAI	DeepSeek	Anthropic	Google
Family	GPT	DeepSeek	Claude	Gemini
Release date	2025-08-07	2025-01-20	2026-04-16	2026-04-22
Context window	400,000 tokens	128,000 tokens	1,000,000 tokens	2,000,000 tokens
Parameters	—	671B	—	—
Modality	text, vision, audio	text	text, vision	text, vision, audio, video
License	proprietary	MIT	proprietary	proprietary
Source	proprietary	open weights	proprietary	proprietary
Description	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.	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	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.	Google DeepMind's flagship multimodal model. Best-in-class for multimodal understanding and agentic / vibe coding workflows. A "Deep Think" reasoning mode is available to AI Ultra subscribers.
Links	vendor →	weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	85.1%	—	88.2%	87.1%
GPQA-D	87.3%	—	90.1%	88.6%
HumanEval	95.2%	—	97.4%	96.5%
Aider	85.4%	—	91.2%	84.8%
AIME-25	91.0%	79.8%	93.5%	92.8%
LiveCB	74.5%	—	80.2%	76.1%
MMMU	74.1%	—	79.0%	84.3%