Compare AI models

Specifications
Parameters
9B/27B1.5B/7B/72B
Context window
8k4k
API pricing
Cheapest input
$0.65NextBit—
Cheapest output
$0.65NextBit—
$163NextBit · int4—
Benchmarks
MATH
42.3%85.9%
GSM8K
74%95.9%
Overview
CompanyGoogleQwen
Release dateJun 27 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Gemma 2 on 2 of the 2 benchmarks they both report (MATH, GSM8K). Gemma 2 shipped 84 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Gemma 2 has 9B/27B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 8k (Gemma 2) vs 4k (Qwen2.5-Math).

On MATH, Qwen2.5-Math leads at 85.9% vs Gemma 2 at 42.3%. On GSM8K, Qwen2.5-Math leads at 95.9% vs Gemma 2 at 74%.