AI Model Release Tracker - Timeline of Major AI Models from 2022-2026

Home/Compare/Gemini 3.0 Flash vs LLaMA 4 Maverick

Gemini 3.0 Flash vs LLaMA 4 Maverick

2 vs 0 benchmarks won

Google
Gemini 3.0 Flash
Meta
LLaMA 4 Maverick
Overview
CompanyGoogleMeta
Release dateDec 17 2025Apr 5 2025
Model type
Open sourceNoYes
Specifications
Parameters
Context window
Benchmarks
Science reasoning
GPQA Diamond
90.4%
Software engineering
SWE-Bench Verified
78%
Multimodal understanding
MMMU
Timeline
Release gapLLaMA 4 Maverick shipped 256 days before Gemini 3.0 Flash

Which is better: Gemini 3.0 Flash or LLaMA 4 Maverick?

Gemini 3.0 Flash leads LLaMA 4 Maverick on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). LLaMA 4 Maverick shipped 256 days before Gemini 3.0 Flash, so benchmark comparisons should account for the intervening progress.

LLaMA 4 Maverick is an open-source / open-weight model; Gemini 3.0 Flash is proprietary.

Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.

Frequently asked questions

When was Gemini 3.0 Flash released?
Gemini 3.0 Flash was released by Google on Dec 17 2025.
When was LLaMA 4 Maverick released?
LLaMA 4 Maverick was released by Meta on Apr 5 2025.
Is Gemini 3.0 Flash or LLaMA 4 Maverick open source?
LLaMA 4 Maverick is an open-source / open-weight model released by Meta. Gemini 3.0 Flash is a proprietary model released by Google.

Other comparisons