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

DeepSeek-V4-Pro×

DeepSeek-R1×

Gemini 3.5×

GPT-5×Clear all

	DeepSeek-V4-Pro DeepSeek	DeepSeek-R1 DeepSeek	Gemini 3.5 Google	GPT-5 OpenAI
Vendor	DeepSeek	DeepSeek	Google	OpenAI
Family	DeepSeek	DeepSeek	Gemini	GPT
Release date	2026-04-22	2025-01-20	2026-05-20	2025-08-07
Context window	1,000,000 tokens	128,000 tokens	2,000,000 tokens	400,000 tokens
Parameters	1.6T (49B active)	671B	—	—
Modality	text	text	text, vision, audio, video	text, vision, audio
License	MIT	MIT	proprietary	proprietary
Source	open weights	open weights	proprietary	proprietary
Description	DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs.	Reasoning-focused open-weight model.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.
Links	weights →	weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	84.2%	—	88.9%	85.1%
GPQA-D	82.4%	—	91.2%	87.3%
HumanEval	95.1%	—	—	95.2%
Aider	80.1%	—	—	85.4%
AIME-25	88.6%	79.8%	96.1%	91.0%
LiveCB	72.4%	—	—	74.5%
MMMU	—	—	86.0%	74.1%