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 Pro×

DeepSeek-V4-Flash×

Gemini 3 Pro×

DeepSeek-R1×Clear all

	GPT-5 Pro OpenAI	DeepSeek-V4-Flash DeepSeek	Gemini 3 Pro Google	DeepSeek-R1 DeepSeek
Vendor	OpenAI	DeepSeek	Google	DeepSeek
Family	GPT	DeepSeek	Gemini	DeepSeek
Release date	2025-08-07	2026-04-22	2026-04-22	2025-01-20
Context window	400,000 tokens	1,000,000 tokens	2,000,000 tokens	128,000 tokens
Parameters	—	284B (13B active)	—	671B
Modality	text, vision, audio	text	text, vision, audio, video	text
License	proprietary	MIT	proprietary	MIT
Source	proprietary	open weights	proprietary	open weights
Description	Higher-reasoning variant of GPT-5, used for harder scientific and research tasks (e.g., immunology breakthroughs at NIH). Same 400K context as GPT-5; trades latency for depth.	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.	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.	Reasoning-focused open-weight model.
Links	vendor →	weights →	vendor →	weights →
Benchmarks
MMLU-Pro	—	—	87.1%	—
GPQA-D	—	—	88.6%	—
HumanEval	—	—	96.5%	—
Aider	—	—	84.8%	—
AIME-25	—	—	92.8%	79.8%
LiveCB	—	—	76.1%	—
MMMU	—	—	84.3%	—