Compare AI models

Specifications
Parameters
9B/27B14B
Context window
8k2k
API pricing
Cheapest input
$0.65NextBit—
Cheapest output
$0.65NextBit—
$163NextBit · int4—
Benchmarks
HumanEval
51.8%32.3%
MATH
42.3%24.8%
MMLU
75.2%66.3%
GSM8K
74%61.3%
Overview
CompanyGoogleQwen
Release dateJun 27 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 2 leads Qwen-14B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen-14B shipped 276 days before Gemma 2, so benchmark comparisons should account for the intervening progress.

Gemma 2 has 9B/27B parameters, while Qwen-14B has 14B. Context windows are 8k (Gemma 2) vs 2k (Qwen-14B).

On HumanEval, Gemma 2 leads at 51.8% vs Qwen-14B at 32.3%. On MATH, Gemma 2 leads at 42.3% vs Qwen-14B at 24.8%. On MMLU, Gemma 2 leads at 75.2% vs Qwen-14B at 66.3%. On GSM8K, Gemma 2 leads at 74% vs Qwen-14B at 61.3%.