Compare AI models

Specifications
Parameters
9B/27B14.3B
Context window
8k32k
API pricing
Cheapest input
$0.65NextBit—
Cheapest output
$0.65NextBit—
$163NextBit · int4—
Benchmarks
HumanEval
51.8%34.2%
MMLU
75.2%62.5%
GSM8K
74%61.5%
Overview
CompanyGoogleQwen
Release dateJun 27 2024Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 2 leads Qwen1.5-MoE on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen1.5-MoE shipped 91 days before Gemma 2, so benchmark comparisons should account for the intervening progress.

Gemma 2 has 9B/27B parameters, while Qwen1.5-MoE has 14.3B. Context windows are 8k (Gemma 2) vs 32k (Qwen1.5-MoE).

On HumanEval, Gemma 2 leads at 51.8% vs Qwen1.5-MoE at 34.2%. On MMLU, Gemma 2 leads at 75.2% vs Qwen1.5-MoE at 62.5%. On GSM8K, Gemma 2 leads at 74% vs Qwen1.5-MoE at 61.5%.