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×

Qwen3.6-27B×

Gemini Omni×

DeepSeek-R1×Clear all

	DeepSeek-V3.1 DeepSeek	Qwen3.6-27B Alibaba	Gemini Omni Google	DeepSeek-R1 DeepSeek
Vendor	DeepSeek	Alibaba	Google	DeepSeek
Family	DeepSeek	Qwen	Gemini	DeepSeek
Release date	2025-08-21	2026-04-22	2026-05-20	2025-01-20
Context window	128,000 tokens	262,144 tokens	1,000,000 tokens	128,000 tokens
Parameters	671B	27B (dense)	—	671B
Modality	text	text, vision, video	text, vision, audio, video	text
License	MIT	Apache-2.0	proprietary	MIT
Source	open weights	open weights	proprietary	open weights
Description	Large MoE open-weight model. Predecessor to DeepSeek-V4.	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.	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	Reasoning-focused open-weight model.
Links	weights →	weights →	vendor →	weights →
Benchmarks
MMLU-Pro	—	78.9%	—	—
HumanEval	—	91.5%	—	—
Aider	—	70.2%	—	—
AIME-25	—	—	—	79.8%
MMMU	—	70.3%	82.5%	—