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×

Gemini 3.5×

Gemini 3 Pro×

	DeepSeek-V4-Pro DeepSeek	Gemini 3.5 Google	Gemini 3 Pro Google	o3 OpenAI
Vendor	DeepSeek	Google	Google	OpenAI
Family	DeepSeek	Gemini	Gemini	o-series
Release date	2026-04-22	2026-05-20	2026-04-22	2025-04-16
Context window	1,000,000 tokens	2,000,000 tokens	2,000,000 tokens	200,000 tokens
Parameters	1.6T (49B active)	—	—	—
Modality	text	text, vision, audio, video	text, vision, audio, video	text, vision
License	MIT	proprietary	proprietary	proprietary
Source	open weights	proprietary	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.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	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 model in the o-series.
Links	weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	84.2%	88.9%	87.1%	—
GPQA-D	82.4%	91.2%	88.6%	87.7%
HumanEval	95.1%	—	96.5%	—
Aider	80.1%	—	84.8%	—
AIME-25	88.6%	96.1%	92.8%	88.9%
LiveCB	72.4%	—	76.1%	—
MMMU	—	86.0%	84.3%	—