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

DeepSeek-R1×

Claude 4.7 Opus×

Qwen3.6-27B×

Gemini 3 Pro×Clear all

	DeepSeek-R1 DeepSeek	Claude 4.7 Opus Anthropic	Qwen3.6-27B Alibaba	Gemini 3 Pro Google
Vendor	DeepSeek	Anthropic	Alibaba	Google
Family	DeepSeek	Claude	Qwen	Gemini
Release date	2025-01-20	2026-04-16	2026-04-22	2026-04-22
Context window	128,000 tokens	1,000,000 tokens	262,144 tokens	2,000,000 tokens
Parameters	671B	—	27B (dense)	—
Modality	text	text, vision	text, vision, video	text, vision, audio, video
License	MIT	proprietary	Apache-2.0	proprietary
Source	open weights	proprietary	open weights	proprietary
Description	Reasoning-focused open-weight model.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.	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.	Google DeepMind's flagship multimodal model. Best-in-class for multimodal understanding and agentic / vibe coding workflows. A "Deep Think" reasoning mode is available to AI Ultra subscribers.
Links	weights →	vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	—	88.2%	78.9%	87.1%
GPQA-D	—	90.1%	—	88.6%
HumanEval	—	97.4%	91.5%	96.5%
Aider	—	91.2%	70.2%	84.8%
AIME-25	79.8%	93.5%	—	92.8%
LiveCB	—	80.2%	—	76.1%
MMMU	—	79.0%	70.3%	84.3%