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-V4-Pro×

Gemini Omni×

Qwen3 235B×

Claude 4.6 Sonnet×Clear all

	DeepSeek-V4-Pro DeepSeek	Gemini Omni Google	Qwen3 235B Alibaba	Claude 4.6 Sonnet Anthropic
Vendor	DeepSeek	Google	Alibaba	Anthropic
Family	DeepSeek	Gemini	Qwen	Claude
Release date	2026-04-22	2026-05-20	2025-04-29	2026-02-17
Context window	1,000,000 tokens	1,000,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	1.6T (49B active)	—	235B	—
Modality	text	text, vision, audio, video	text	text, vision
License	MIT	proprietary	Apache-2.0	proprietary
Source	open weights	proprietary	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.	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	Predecessor to the Qwen3.6 family.	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.
Links	weights →	vendor →	weights →
Benchmarks
MMLU-Pro	84.2%	—	—	85.4%
GPQA-D	82.4%	—	—	85.8%
HumanEval	95.1%	—	—	95.9%
Aider	80.1%	—	—	83.6%
AIME-25	88.6%	—	—	87.4%
LiveCB	72.4%	—	—	73.8%
MMMU	—	82.5%	—	—