Compare AI models

Specifications
Parameters
8B30B/480B
Context window
8k256k
API pricing
Cheapest input
—$0.30DeepInfra
Cheapest output
—$1.00DeepInfra
—$110DeepInfra · turbo · fp4
These models have no shared benchmark scores.
Overview
CompanyNVIDIAQwen
Release dateAug 21 2024Jul 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral NeMo Minitron 8B and Qwen3-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral NeMo Minitron 8B shipped 335 days before Qwen3-Coder, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while Qwen3-Coder has 30B/480B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 256k (Qwen3-Coder).

Direct benchmark comparisons are unavailable — Mistral NeMo Minitron 8B and Qwen3-Coder don't publish scores on any of the same benchmarks.