Compare AI models

Specifications
Parameters
9B/27B8B
Context window
8k4k
API pricing
Cheapest input
$0.65NextBit—
Cheapest output
$0.65NextBit—
$163NextBit · int4—
Benchmarks
HellaSwag
86.4%76.4%
MMLU
75.2%54.4%
Overview
CompanyGoogleNVIDIA
Release dateJun 27 2024Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 2 leads Nemotron-3 8B on 2 of the 2 benchmarks they both report (HellaSwag, MMLU). Nemotron-3 8B shipped 225 days before Gemma 2, so benchmark comparisons should account for the intervening progress.

Gemma 2 has 9B/27B parameters, while Nemotron-3 8B has 8B. Context windows are 8k (Gemma 2) vs 4k (Nemotron-3 8B).

On HellaSwag, Gemma 2 leads at 86.4% vs Nemotron-3 8B at 76.4%. On MMLU, Gemma 2 leads at 75.2% vs Nemotron-3 8B at 54.4%.