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×

Qwen3.6-27B×

Claude 4.7 Opus×Clear all

	Grok 4 xAI	DeepSeek-V4-Pro DeepSeek	Qwen3.6-27B Alibaba	Claude 4.7 Opus Anthropic
Vendor	xAI	DeepSeek	Alibaba	Anthropic
Family	Grok	DeepSeek	Qwen	Claude
Release date	2025-07-09	2026-04-22	2026-04-22	2026-04-16
Context window	256,000 tokens	1,000,000 tokens	262,144 tokens	1,000,000 tokens
Parameters	—	1.6T (49B active)	27B (dense)	—
Modality	text	text	text, vision, video	text, vision
License	proprietary	MIT	Apache-2.0	proprietary
Source	proprietary	open weights	open weights	proprietary
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.	Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.
Links	vendor →	weights →	weights →	vendor →
Benchmarks
MMLU-Pro	82.8%	84.2%	78.9%	88.2%
GPQA-D	87.5%	82.4%	—	90.1%
HumanEval	—	95.1%	91.5%	97.4%
Aider	72.5%	80.1%	70.2%	91.2%
AIME-25	86.1%	88.6%	—	93.5%
LiveCB	65.3%	72.4%	—	80.2%
MMMU	—	—	70.3%	79.0%