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

Gemini 3.5×

GPT-5×

DeepSeek-V4-Pro×

GPT-5.5×Clear all

	Gemini 3.5 Google	GPT-5 OpenAI	DeepSeek-V4-Pro DeepSeek	GPT-5.5 OpenAI
Vendor	Google	OpenAI	DeepSeek	OpenAI
Family	Gemini	GPT	DeepSeek	GPT
Release date	2026-05-20	2025-08-07	2026-04-22	2026-04-23
Context window	2,000,000 tokens	400,000 tokens	1,000,000 tokens	400,000 tokens
Parameters	—	—	1.6T (49B active)	—
Modality	text, vision, audio, video	text, vision, audio	text	text, vision, audio
License	proprietary	proprietary	MIT	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	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 Superseded by GPT-5.5 in April 2026.	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.	OpenAI's smartest and most intuitive model — successor to GPT-5, with major coding, research, and document workflow gains. GPT-5.5 Pro variant also available for heavier reasoning.
Links	vendor →	vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	88.9%	85.1%	84.2%	87.6%
GPQA-D	91.2%	87.3%	82.4%	89.4%
HumanEval	—	95.2%	95.1%	96.8%
Aider	—	85.4%	80.1%	89.7%
AIME-25	96.1%	91.0%	88.6%	94.2%
LiveCB	—	74.5%	72.4%	78.9%
MMMU	86.0%	74.1%	—	78.4%