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

Grok 4×

DeepSeek-V4-Pro×

Claude 4.8 Opus×

Qwen3 235B×Clear all

	Grok 4 xAI	DeepSeek-V4-Pro DeepSeek	Claude 4.8 Opus Anthropic	Qwen3 235B Alibaba
Vendor	xAI	DeepSeek	Anthropic	Alibaba
Family	Grok	DeepSeek	Claude	Qwen
Release date	2025-07-09	2026-04-22	2026-05-28	2025-04-29
Context window	256,000 tokens	1,000,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	1.6T (49B active)	—	235B
Modality	text	text	text, vision	text
License	proprietary	MIT	proprietary	Apache-2.0
Source	proprietary	open weights	proprietary	open weights
Description	—	DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs.	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.	Predecessor to the Qwen3.6 family.
Links	vendor →	weights →	vendor →	weights →
Benchmarks
MMLU-Pro	82.8%	84.2%	—	—
GPQA-D	87.5%	82.4%	—	—
HumanEval	—	95.1%	—	—
Aider	72.5%	80.1%	—	—
AIME-25	86.1%	88.6%	—	—
LiveCB	65.3%	72.4%	—	—