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

Llama 4 Scout×

o3×

DeepSeek-V4-Pro×

DeepSeek-R1×Clear all

	Llama 4 Scout Meta	o3 OpenAI	DeepSeek-V4-Pro DeepSeek	DeepSeek-R1 DeepSeek
Vendor	Meta	OpenAI	DeepSeek	DeepSeek
Family	Llama	o-series	DeepSeek	DeepSeek
Release date	2025-04-05	2025-04-16	2026-04-22	2025-01-20
Context window	10,000,000 tokens	200,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	109B	—	1.6T (49B active)	671B
Modality	text, vision	text, vision	text	text
License	Llama 4 Community License	proprietary	MIT	MIT
Source	open weights	proprietary	open weights	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.	Reasoning-focused open-weight model.
Links	weights →		weights →	weights →
Benchmarks
MMLU-Pro	—	—	84.2%	—
GPQA-D	—	87.7%	82.4%	—
HumanEval	—	—	95.1%	—
Aider	—	—	80.1%	—
AIME-25	—	88.9%	88.6%	79.8%
LiveCB	—	—	72.4%	—