Compare AI models

Specifications
Parameters
8B/70B/405B0.8B/2B/4B/9B
Context window
128k256k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
49%81.7%
MMLU-Pro
73.3%82.5%
Overview
CompanyMetaQwen
Release dateJul 23 2024Mar 2 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Small leads LLaMA 3.1 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU-Pro). LLaMA 3.1 shipped 587 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 128k (LLaMA 3.1) vs 256k (Qwen3.5 Small).

On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs LLaMA 3.1 at 49%. On MMLU-Pro, Qwen3.5 Small leads at 82.5% vs LLaMA 3.1 at 73.3%.