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

GPT-5 Pro×

Gemini 3 Pro×

Mistral Large 2×

DeepSeek-V4-Flash×Clear all

	GPT-5 Pro OpenAI	Gemini 3 Pro Google	Mistral Large 2 Mistral	DeepSeek-V4-Flash DeepSeek
Vendor	OpenAI	Google	Mistral	DeepSeek
Family	GPT	Gemini	Mistral	DeepSeek
Release date	2025-08-07	2026-04-22	2024-07-24	2026-04-22
Context window	400,000 tokens	2,000,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	—	—	123B	284B (13B active)
Modality	text, vision, audio	text, vision, audio, video	text	text
License	proprietary	proprietary	Mistral Research License	MIT
Source	proprietary	proprietary	open weights	open weights
Description	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.	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.	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.
Links	vendor →	vendor →	vendor →weights →	weights →
Benchmarks
MMLU-Pro	—	87.1%	—	—
GPQA-D	—	88.6%	—	—
HumanEval	—	96.5%	89.0%	—
Aider	—	84.8%	—	—
AIME-25	—	92.8%	—	—
LiveCB	—	76.1%	—	—
MMMU	—	84.3%	—	—