AI Model Release Tracker - Analytics

Gemini 3.5 Flash-LitevsCode Llama 70B

Gemini 3.5 Flash-Lite
Code Llama 70B
Benchmarks
Agentic coding
SWE-Bench Pro
54.2%
Agentic terminal coding
Terminal-Bench 2.1
54%
Browser agent
BU Bench
49%
Agentic computer use
OSWorld-Verified
74%
Knowledge work
GDPval-AA v2
1140
Timeline
Release gapCode Llama 70B shipped 904 days before Gemini 3.5 Flash-Lite
Overview
CompanyGoogleMeta
Release dateJul 21 2026Jan 29 2024
AccessProprietaryOpen Weight

Which is better: Gemini 3.5 Flash-Lite or Code Llama 70B?

Gemini 3.5 Flash-Lite and Code Llama 70B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama 70B shipped 904 days before Gemini 3.5 Flash-Lite, so benchmark comparisons should account for the intervening progress.

Gemini 3.5 Flash-Lite is proprietary, while Code Llama 70B is open weight.

Direct benchmark comparisons are unavailable — Gemini 3.5 Flash-Lite and Code Llama 70B don't publish scores on any of the same benchmarks.

Frequently asked questions

Gemini 3.5 Flash-Lite was released by Google on Jul 21 2026.

Code Llama 70B was released by Meta on Jan 29 2024.

Gemini 3.5 Flash-Lite is a proprietary model released by Google. Code Llama 70B is an open weight model released by Meta.

Other comparisons