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 Pro×

Claude 4.7 Opus×

Gemini 3.5×

DeepSeek-R1×Clear all

	Gemini 3 Pro Google	Claude 4.7 Opus Anthropic	Gemini 3.5 Google	DeepSeek-R1 DeepSeek
Vendor	Google	Anthropic	Google	DeepSeek
Family	Gemini	Claude	Gemini	DeepSeek
Release date	2026-04-22	2026-04-16	2026-05-20	2025-01-20
Context window	2,000,000 tokens	1,000,000 tokens	2,000,000 tokens	128,000 tokens
Parameters	—	—	—	671B
Modality	text, vision, audio, video	text, vision	text, vision, audio, video	text
License	proprietary	proprietary	proprietary	MIT
Source	proprietary	proprietary	proprietary	open weights
Description	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.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Reasoning-focused open-weight model.
Links	vendor →	vendor →	vendor →	weights →
Benchmarks
MMLU-Pro	87.1%	88.2%	88.9%	—
GPQA-D	88.6%	90.1%	91.2%	—
HumanEval	96.5%	97.4%	—	—
Aider	84.8%	91.2%	—	—
AIME-25	92.8%	93.5%	96.1%	79.8%
LiveCB	76.1%	80.2%	—	—
MMMU	84.3%	79.0%	86.0%	—