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

Qwen3.6-27B×

DeepSeek-V4-Pro×

Claude 4.7 Opus×

Grok 4×Clear all

	Qwen3.6-27B Alibaba	DeepSeek-V4-Pro DeepSeek	Claude 4.7 Opus Anthropic	Grok 4 xAI
Vendor	Alibaba	DeepSeek	Anthropic	xAI
Family	Qwen	DeepSeek	Claude	Grok
Release date	2026-04-22	2026-04-22	2026-04-16	2025-07-09
Context window	262,144 tokens	1,000,000 tokens	1,000,000 tokens	256,000 tokens
Parameters	27B (dense)	1.6T (49B active)	—	—
Modality	text, vision, video	text	text, vision	text
License	Apache-2.0	MIT	proprietary	proprietary
Source	open weights	open weights	proprietary	proprietary
Description	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.	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	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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	weights →	weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	78.9%	84.2%	88.2%	82.8%
GPQA-D	—	82.4%	90.1%	87.5%
HumanEval	91.5%	95.1%	97.4%	—
Aider	70.2%	80.1%	91.2%	72.5%
AIME-25	—	88.6%	93.5%	86.1%
LiveCB	—	72.4%	80.2%	65.3%
MMMU	70.3%	—	79.0%	—