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×

GPT-5.6 Sol×

Gemini 3 Pro×

Grok 4×Clear all

	GPT-5 Pro OpenAI	GPT-5.6 Sol OpenAI	Gemini 3 Pro Google	Grok 4 xAI
Vendor	OpenAI	OpenAI	Google	xAI
Family	GPT	GPT	Gemini	Grok
Release date	2025-08-07	2026-06-26	2026-04-22	2025-07-09
Context window	400,000 tokens	—	2,000,000 tokens	256,000 tokens
Parameters	—	—	—	—
Modality	text, vision, audio	text, vision, audio	text, vision, audio, video	text
License	proprietary	proprietary	proprietary	proprietary
Source	proprietary	proprietary	proprietary	proprietary
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.	Flagship of OpenAI's GPT-5.6 three-model suite (Sol / Terra / Luna), released as a limited preview. Strong gains in coding, cybersecurity, biology, and long-horizon agentic work. Pricing: $5 / $30 per million input/output tokens.	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.	—
Links	vendor →	vendor →	vendor →	vendor →
Benchmarks
MMLU-Pro	—	—	87.1%	82.8%
GPQA-D	—	—	88.6%	87.5%
HumanEval	—	—	96.5%	—
Aider	—	—	84.8%	72.5%
AIME-25	—	—	92.8%	86.1%
LiveCB	—	—	76.1%	65.3%
MMMU	—	—	84.3%	—