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-5.5×

DeepSeek-V3.1×

Claude 4.8 Opus×

Grok 4×Clear all

	GPT-5.5 OpenAI	DeepSeek-V3.1 DeepSeek	Claude 4.8 Opus Anthropic	Grok 4 xAI
Vendor	OpenAI	DeepSeek	Anthropic	xAI
Family	GPT	DeepSeek	Claude	Grok
Release date	2026-04-23	2025-08-21	2026-05-28	2025-07-09
Context window	400,000 tokens	128,000 tokens	1,000,000 tokens	256,000 tokens
Parameters	—	671B	—	—
Modality	text, vision, audio	text	text, vision	text
License	proprietary	MIT	proprietary	proprietary
Source	proprietary	open weights	proprietary	proprietary
Description	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.	Large MoE open-weight model. Predecessor to DeepSeek-V4.	Anthropic's flagship hybrid-reasoning model — Opus 4.8 pushes coding and AI-agent workflows further (agentic coding 69.2% vs 64.3% on 4.7; multidisciplinary reasoning 57.9% vs 54.7%). 1M-token context, $5/$25 per MTok pricing held flat from Opus 4.7. Introduces Dynamic Workflows for Claude Code (research preview). GA on Anthropic API (`claude-opus-4-8`), AWS Bedrock, Google Vertex, Microsoft Foundry, and GitHub Copilot.	—
Links	vendor →	weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	87.6%	—	—	82.8%
GPQA-D	89.4%	—	—	87.5%
HumanEval	96.8%	—	—	—
Aider	89.7%	—	—	72.5%
AIME-25	94.2%	—	—	86.1%
LiveCB	78.9%	—	—	65.3%
MMMU	78.4%	—	—	—