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×

Mistral Large 2×

Gemini 2.5 Flash×

	GPT-5.6 Sol OpenAI	Mistral Large 2 Mistral	Gemini 2.5 Flash Google	o3 OpenAI
Vendor	OpenAI	Mistral	Google	OpenAI
Family	GPT	Mistral	Gemini	o-series
Release date	2026-06-26	2024-07-24	2025-06-17	2025-04-16
Context window	—	128,000 tokens	1,000,000 tokens	200,000 tokens
Parameters	—	123B	—	—
Modality	text, vision, audio	text	text, vision, audio	text, vision
License	proprietary	Mistral Research License	proprietary	proprietary
Source	proprietary	open weights	proprietary	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.	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.	Google's cost-and-latency-optimized Gemini 2.5 variant. Generally available June 2025 — designed for high-throughput agentic workflows with sub-second first-token latency.	Reasoning-focused model in the o-series.
Links	vendor →	vendor →weights →
Benchmarks
GPQA-D	—	—	—	87.7%
HumanEval	—	89.0%	—	—
AIME-25	—	—	—	88.9%