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 Pro×

Mistral Large 2×

GPT-5.5×

Qwen3 235B×Clear all

	Gemini 3 Pro Google	Mistral Large 2 Mistral	GPT-5.5 OpenAI	Qwen3 235B Alibaba
Vendor	Google	Mistral	OpenAI	Alibaba
Family	Gemini	Mistral	GPT	Qwen
Release date	2026-04-22	2024-07-24	2026-04-23	2025-04-29
Context window	2,000,000 tokens	128,000 tokens	400,000 tokens	128,000 tokens
Parameters	—	123B	—	235B
Modality	text, vision, audio, video	text	text, vision, audio	text
License	proprietary	Mistral Research License	proprietary	Apache-2.0
Source	proprietary	open weights	proprietary	open weights
Description	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.	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.	Predecessor to the Qwen3.6 family.
Links	vendor →	vendor →weights →	vendor →	weights →
Benchmarks
MMLU-Pro	87.1%	—	87.6%	—
GPQA-D	88.6%	—	89.4%	—
HumanEval	96.5%	89.0%	96.8%	—
Aider	84.8%	—	89.7%	—
AIME-25	92.8%	—	94.2%	—
LiveCB	76.1%	—	78.9%	—
MMMU	84.3%	—	78.4%	—