Compare AI models

Specifications
Parameters
9B/27B110B
Context window
8k32k
API pricing
Cheapest input
$0.65NextBit—
Cheapest output
$0.65NextBit—
$163NextBit · int4—
Benchmarks
HumanEval
51.8%52.4%
MATH
42.3%49.6%
HellaSwag
86.4%87.5%
MMLU
75.2%80.4%
GSM8K
74%85.4%
Overview
CompanyGoogleQwen
Release dateJun 27 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads Gemma 2 on 5 of the 5 benchmarks they both report. Qwen1.5-110B shipped 63 days before Gemma 2, so benchmark comparisons should account for the intervening progress.

Gemma 2 has 9B/27B parameters, while Qwen1.5-110B has 110B. Context windows are 8k (Gemma 2) vs 32k (Qwen1.5-110B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs Gemma 2 at 51.8%. On MATH, Qwen1.5-110B leads at 49.6% vs Gemma 2 at 42.3%. On HellaSwag, Qwen1.5-110B leads at 87.5% vs Gemma 2 at 86.4%. On MMLU, Qwen1.5-110B leads at 80.4% vs Gemma 2 at 75.2%. On GSM8K, Qwen1.5-110B leads at 85.4% vs Gemma 2 at 74%.