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

o3×

DeepSeek-V4-Pro×

Claude 4.6 Sonnet×

Qwen3.6-27B×Clear all

	o3 OpenAI	DeepSeek-V4-Pro DeepSeek	Claude 4.6 Sonnet Anthropic	Qwen3.6-27B Alibaba
Vendor	OpenAI	DeepSeek	Anthropic	Alibaba
Family	o-series	DeepSeek	Claude	Qwen
Release date	2025-04-16	2026-04-22	2026-02-17	2026-04-22
Context window	200,000 tokens	1,000,000 tokens	1,000,000 tokens	262,144 tokens
Parameters	—	1.6T (49B active)	—	27B (dense)
Modality	text, vision	text	text, vision	text, vision, video
License	proprietary	MIT	proprietary	Apache-2.0
Source	proprietary	open weights	proprietary	open weights
Description	Reasoning-focused model in the o-series.	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 mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.	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.
Links		weights →		weights →
Benchmarks
MMLU-Pro	—	84.2%	85.4%	78.9%
GPQA-D	87.7%	82.4%	85.8%	—
HumanEval	—	95.1%	95.9%	91.5%
Aider	—	80.1%	83.6%	70.2%
AIME-25	88.9%	88.6%	87.4%	—
LiveCB	—	72.4%	73.8%	—
MMMU	—	—	—	70.3%