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×

DeepSeek-V3.1×

Gemini 3.5×

Claude 4.6 Sonnet×Clear all

	DeepSeek-R1 DeepSeek	DeepSeek-V3.1 DeepSeek	Gemini 3.5 Google	Claude 4.6 Sonnet Anthropic
Vendor	DeepSeek	DeepSeek	Google	Anthropic
Family	DeepSeek	DeepSeek	Gemini	Claude
Release date	2025-01-20	2025-08-21	2026-05-20	2026-02-17
Context window	128,000 tokens	128,000 tokens	2,000,000 tokens	1,000,000 tokens
Parameters	671B	671B	—	—
Modality	text	text	text, vision, audio, video	text, vision
License	MIT	MIT	proprietary	proprietary
Source	open weights	open weights	proprietary	proprietary
Description	Reasoning-focused open-weight model.	Large MoE open-weight model. Predecessor to DeepSeek-V4.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	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 →	weights →	vendor →
Benchmarks
MMLU-Pro	—	—	88.9%	85.4%
GPQA-D	—	—	91.2%	85.8%
HumanEval	—	—	—	95.9%
Aider	—	—	—	83.6%
AIME-25	79.8%	—	96.1%	87.4%
LiveCB	—	—	—	73.8%
MMMU	—	—	86.0%	—