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×

Mistral Large 2×

Gemini 3 Pro×

Grok 4×Clear all

	DeepSeek-V4-Pro DeepSeek	Mistral Large 2 Mistral	Gemini 3 Pro Google	Grok 4 xAI
Vendor	DeepSeek	Mistral	Google	xAI
Family	DeepSeek	Mistral	Gemini	Grok
Release date	2026-04-22	2024-07-24	2026-04-22	2025-07-09
Context window	1,000,000 tokens	128,000 tokens	2,000,000 tokens	256,000 tokens
Parameters	1.6T (49B active)	123B	—	—
Modality	text	text	text, vision, audio, video	text
License	MIT	Mistral Research License	proprietary	proprietary
Source	open weights	open weights	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.	Large text-only Mistral model with a 128K context window and 123B parameters, tuned for strong instruction following and long-context reasoning. Mistral's flagship open-weights release in the Large 2 line.	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.	—
Links	weights →	vendor →weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	84.2%	—	87.1%	82.8%
GPQA-D	82.4%	—	88.6%	87.5%
HumanEval	95.1%	89.0%	96.5%	—
Aider	80.1%	—	84.8%	72.5%
AIME-25	88.6%	—	92.8%	86.1%
LiveCB	72.4%	—	76.1%	65.3%
MMMU	—	—	84.3%	—