Compare AI models

Specifications
Parameters
9B/27B—
Context window
8k1M
API pricing
Cheapest input
$0.65NextBit—
Cheapest output
$0.65NextBit—
$163NextBit · int4—
Benchmarks
HumanEval
51.8%86.6%
MATH
42.3%81.1%
GSM8K
74%93.8%
Overview
CompanyGoogleQwen
Release dateJun 27 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads Gemma 2 on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). Gemma 2 shipped 141 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Gemma 2) vs 1M (Qwen2.5-Turbo (1M)). Gemma 2 is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs Gemma 2 at 51.8%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs Gemma 2 at 42.3%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs Gemma 2 at 74%.