Compare AI models

Specifications
Parameters
24B110B
Context window
32k32k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.064DeepInfra—
$14.00DeepInfra · fp8—
Benchmarks
HumanEval
84.8%52.4%
MATH
70.6%49.6%
Overview
CompanyMistralQwen
Release dateJan 30 2025Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3 leads Qwen1.5-110B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Qwen1.5-110B shipped 280 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.

Mistral Small 3 has 24B parameters, while Qwen1.5-110B has 110B. Context windows are 32k (Mistral Small 3) vs 32k (Qwen1.5-110B).

On HumanEval, Mistral Small 3 leads at 84.8% vs Qwen1.5-110B at 52.4%. On MATH, Mistral Small 3 leads at 70.6% vs Qwen1.5-110B at 49.6%.