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

Gemini 3.5×

DeepSeek-V4-Pro×

Claude 4.6 Sonnet×

DeepSeek-R1×Clear all

	Gemini 3.5 Google	DeepSeek-V4-Pro DeepSeek	Claude 4.6 Sonnet Anthropic	DeepSeek-R1 DeepSeek
Vendor	Google	DeepSeek	Anthropic	DeepSeek
Family	Gemini	DeepSeek	Claude	DeepSeek
Release date	2026-05-20	2026-04-22	2026-02-17	2025-01-20
Context window	2,000,000 tokens	1,000,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	1.6T (49B active)	—	671B
Modality	text, vision, audio, video	text	text, vision	text
License	proprietary	MIT	proprietary	MIT
Source	proprietary	open weights	proprietary	open weights
Description	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	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.	Reasoning-focused open-weight model.
Links	vendor →	weights →		weights →
Benchmarks
MMLU-Pro	88.9%	84.2%	85.4%	—
GPQA-D	91.2%	82.4%	85.8%	—
HumanEval	—	95.1%	95.9%	—
Aider	—	80.1%	83.6%	—
AIME-25	96.1%	88.6%	87.4%	79.8%
LiveCB	—	72.4%	73.8%	—
MMMU	86.0%	—	—	—