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

Gemini 3.5×

Mistral Large 2×

GPT-5.5×

DeepSeek-V4-Flash×Clear all

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