Compare AI models

Specifications
Parameters
400B1.5B/7B/72B
Context window
1M4k
API pricing
Cheapest input
$0.35Parasail—
Cheapest output
$1.00Parasail—
$120Parasail · fp8—
These models have no shared benchmark scores.
Overview
CompanyMetaQwen
Release dateApr 5 2025Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 4 Maverick and Qwen2.5-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Math shipped 198 days before LLaMA 4 Maverick, so benchmark comparisons should account for the intervening progress.

LLaMA 4 Maverick has 400B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 1M (LLaMA 4 Maverick) vs 4k (Qwen2.5-Math).

Direct benchmark comparisons are unavailable — LLaMA 4 Maverick and Qwen2.5-Math don't publish scores on any of the same benchmarks.