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-Flash×

Gemini 3.5×

GPT-5.5×

Mistral Large 2×Clear all

	DeepSeek-V4-Flash DeepSeek	Gemini 3.5 Google	GPT-5.5 OpenAI	Mistral Large 2 Mistral
Vendor	DeepSeek	Google	OpenAI	Mistral
Family	DeepSeek	Gemini	GPT	Mistral
Release date	2026-04-22	2026-05-20	2026-04-23	2024-07-24
Context window	1,000,000 tokens	2,000,000 tokens	400,000 tokens	128,000 tokens
Parameters	284B (13B active)	—	—	123B
Modality	text	text, vision, audio, video	text, vision, audio	text
License	MIT	proprietary	proprietary	Mistral Research License
Source	open weights	proprietary	proprietary	open weights
Description	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	OpenAI's smartest and most intuitive model — successor to GPT-5, with major coding, research, and document workflow gains. GPT-5.5 Pro variant also available for heavier reasoning.	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 →	vendor →weights →
Benchmarks
MMLU-Pro	—	88.9%	87.6%	—
GPQA-D	—	91.2%	89.4%	—
HumanEval	—	—	96.8%	89.0%
Aider	—	—	89.7%	—
AIME-25	—	96.1%	94.2%	—
LiveCB	—	—	78.9%	—
MMMU	—	86.0%	78.4%	—