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-R1×

Gemini 3 Pro×

GPT-5 Pro×

Qwen3.6-27B×Clear all

	DeepSeek-R1 DeepSeek	Gemini 3 Pro Google	GPT-5 Pro OpenAI	Qwen3.6-27B Alibaba
Vendor	DeepSeek	Google	OpenAI	Alibaba
Family	DeepSeek	Gemini	GPT	Qwen
Release date	2025-01-20	2026-04-22	2025-08-07	2026-04-22
Context window	128,000 tokens	2,000,000 tokens	400,000 tokens	262,144 tokens
Parameters	671B	—	—	27B (dense)
Modality	text	text, vision, audio, video	text, vision, audio	text, vision, video
License	MIT	proprietary	proprietary	Apache-2.0
Source	open weights	proprietary	proprietary	open weights
Description	Reasoning-focused open-weight model.	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.	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.	Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input.
Links	weights →	vendor →	vendor →	weights →
Benchmarks
MMLU-Pro	—	87.1%	—	78.9%
GPQA-D	—	88.6%	—	—
HumanEval	—	96.5%	—	91.5%
Aider	—	84.8%	—	70.2%
AIME-25	79.8%	92.8%	—	—
LiveCB	—	76.1%	—	—
MMMU	—	84.3%	—	70.3%