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×

Qwen3.6-27B×

Grok 4×Clear all

	DeepSeek-V4-Pro DeepSeek	Gemini 3.5 Google	Qwen3.6-27B Alibaba	Grok 4 xAI
Vendor	DeepSeek	Google	Alibaba	xAI
Family	DeepSeek	Gemini	Qwen	Grok
Release date	2026-04-22	2026-05-20	2026-04-22	2025-07-09
Context window	1,000,000 tokens	2,000,000 tokens	262,144 tokens	256,000 tokens
Parameters	1.6T (49B active)	—	27B (dense)	—
Modality	text	text, vision, audio, video	text, vision, video	text
License	MIT	proprietary	Apache-2.0	proprietary
Source	open weights	proprietary	open weights	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.	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 →	weights →	vendor →
Benchmarks
MMLU-Pro	84.2%	88.9%	78.9%	82.8%
GPQA-D	82.4%	91.2%	—	87.5%
HumanEval	95.1%	—	91.5%	—
Aider	80.1%	—	70.2%	72.5%
AIME-25	88.6%	96.1%	—	86.1%
LiveCB	72.4%	—	—	65.3%
MMMU	—	86.0%	70.3%	—