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-V3.1×

GPT-5.5×

Gemini 3.5×

GPT-5×Clear all

	DeepSeek-V3.1 DeepSeek	GPT-5.5 OpenAI	Gemini 3.5 Google	GPT-5 OpenAI
Vendor	DeepSeek	OpenAI	Google	OpenAI
Family	DeepSeek	GPT	Gemini	GPT
Release date	2025-08-21	2026-04-23	2026-05-20	2025-08-07
Context window	128,000 tokens	400,000 tokens	2,000,000 tokens	400,000 tokens
Parameters	671B	—	—	—
Modality	text	text, vision, audio	text, vision, audio, video	text, vision, audio
License	MIT	proprietary	proprietary	proprietary
Source	open weights	proprietary	proprietary	proprietary
Description	Large MoE open-weight model. Predecessor to DeepSeek-V4.	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.	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 Superseded by GPT-5.5 in April 2026.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 →	vendor →	vendor →	vendor →
Benchmarks
MMLU-Pro	—	87.6%	88.9%	85.1%
GPQA-D	—	89.4%	91.2%	87.3%
HumanEval	—	96.8%	—	95.2%
Aider	—	89.7%	—	85.4%
AIME-25	—	94.2%	96.1%	91.0%
LiveCB	—	78.9%	—	74.5%
MMMU	—	78.4%	86.0%	74.1%