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-5.6 Sol×

Claude 4.7 Opus×

Mistral Large 2×

	GPT-5.6 Sol OpenAI	Claude 4.7 Opus Anthropic	Mistral Large 2 Mistral	o3 OpenAI
Vendor	OpenAI	Anthropic	Mistral	OpenAI
Family	GPT	Claude	Mistral	o-series
Release date	2026-06-26	2026-04-16	2024-07-24	2025-04-16
Context window	—	1,000,000 tokens	128,000 tokens	200,000 tokens
Parameters	—	—	123B	—
Modality	text, vision, audio	text, vision	text	text, vision
License	proprietary	proprietary	Mistral Research License	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	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.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle). Optimized for complex reasoning and coding. Improved software engineering, long-running coding tasks, and higher-resolution vision over Claude 4.6.	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.	Reasoning-focused model in the o-series.
Links	vendor →	vendor →	vendor →weights →
Benchmarks
MMLU-Pro	—	88.2%	—	—
GPQA-D	—	90.1%	—	87.7%
HumanEval	—	97.4%	89.0%	—
Aider	—	91.2%	—	—
AIME-25	—	93.5%	—	88.9%
LiveCB	—	80.2%	—	—
MMMU	—	79.0%	—	—