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×

Mistral Large 2×

Grok 4×

GPT-5.6 Sol×Clear all

	GPT-5 Pro OpenAI	Mistral Large 2 Mistral	Grok 4 xAI	GPT-5.6 Sol OpenAI
Vendor	OpenAI	Mistral	xAI	OpenAI
Family	GPT	Mistral	Grok	GPT
Release date	2025-08-07	2024-07-24	2025-07-09	2026-06-26
Context window	400,000 tokens	128,000 tokens	256,000 tokens	—
Parameters	—	123B	—	—
Modality	text, vision, audio	text	text	text, vision, audio
License	proprietary	Mistral Research License	proprietary	proprietary
Source	proprietary	open weights	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.	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.	—	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.
Links	vendor →	vendor →weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	—	—	82.8%	—
GPQA-D	—	—	87.5%	—
HumanEval	—	89.0%	—	—
Aider	—	—	72.5%	—
AIME-25	—	—	86.1%	—
LiveCB	—	—	65.3%	—