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

Mistral Large 2×

Gemini 3.5 Flash×

DeepSeek-R1×

GPT-5 Pro×Clear all

	Mistral Large 2 Mistral	Gemini 3.5 Flash Google	DeepSeek-R1 DeepSeek	GPT-5 Pro OpenAI
Vendor	Mistral	Google	DeepSeek	OpenAI
Family	Mistral	Gemini	DeepSeek	GPT
Release date	2024-07-24	2026-05-20	2025-01-20	2025-08-07
Context window	128,000 tokens	—	128,000 tokens	400,000 tokens
Parameters	123B	—	671B	—
Modality	text	text, vision, audio	text	text, vision, audio
License	Mistral Research License	proprietary	MIT	proprietary
Source	open weights	proprietary	open weights	proprietary
Description	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.	Fast, low-cost tier of the Gemini 3.5 family announced at Google I/O 2026. June 2026 update added native computer-use capability, moving Flash from generation to agentic task execution.	Reasoning-focused open-weight model.	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.
Links	vendor →weights →	vendor →	weights →	vendor →
Benchmarks
HumanEval	89.0%	—	—	—
AIME-25	—	—	79.8%	—