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×

Mistral Large 2×

Grok 4×Clear all

	DeepSeek-R1 DeepSeek	Gemini 3 Pro Google	Mistral Large 2 Mistral	Grok 4 xAI
Vendor	DeepSeek	Google	Mistral	xAI
Family	DeepSeek	Gemini	Mistral	Grok
Release date	2025-01-20	2026-04-22	2024-07-24	2025-07-09
Context window	128,000 tokens	2,000,000 tokens	128,000 tokens	256,000 tokens
Parameters	671B	—	123B	—
Modality	text	text, vision, audio, video	text	text
License	MIT	proprietary	Mistral Research License	proprietary
Source	open weights	proprietary	open weights	proprietary
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.	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.	—
Links	weights →	vendor →	vendor →weights →	vendor →
Benchmarks
MMLU-Pro	—	87.1%	—	82.8%
GPQA-D	—	88.6%	—	87.5%
HumanEval	—	96.5%	89.0%	—
Aider	—	84.8%	—	72.5%
AIME-25	79.8%	92.8%	—	86.1%
LiveCB	—	76.1%	—	65.3%
MMMU	—	84.3%	—	—