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 Maverick×

Gemini 2.5 Flash×

Gemini Omni×

DeepSeek-V4-Pro×Clear all

	Llama 4 Maverick Meta	Gemini 2.5 Flash Google	Gemini Omni Google	DeepSeek-V4-Pro DeepSeek
Vendor	Meta	Google	Google	DeepSeek
Family	Llama	Gemini	Gemini	DeepSeek
Release date	2025-04-05	2025-06-17	2026-05-20	2026-04-22
Context window	1,000,000 tokens	1,000,000 tokens	1,000,000 tokens	1,000,000 tokens
Parameters	400B	—	—	1.6T (49B active)
Modality	text, vision	text, vision, audio	text, vision, audio, video	text
License	Llama 4 Community License	proprietary	proprietary	MIT
Source	open weights	proprietary	proprietary	open weights
Description	Mixture-of-experts open-weight model from Meta.	Google's cost-and-latency-optimized Gemini 2.5 variant. Generally available June 2025 — designed for high-throughput agentic workflows with sub-second first-token latency.	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	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.
Links	weights →		vendor →	weights →
Benchmarks
MMLU-Pro	80.5%	—	—	84.2%
GPQA-D	—	—	—	82.4%
HumanEval	—	—	—	95.1%
Aider	—	—	—	80.1%
AIME-25	—	—	—	88.6%
LiveCB	—	—	—	72.4%
MMMU	68.5%	—	82.5%	—