Benchmark Hub

Lyria 3 Pro Preview has the larger context window (1,048,576 vs 32,768 tokens, 32.0×). Qwen2.5 7B Instruct is open-weights; the other is not.

Lyria 3 Pro Preview detailsQwen2.5 7B Instruct detailsOpen in compare toolLyria 3 Pro Preview on OpenRouterQwen2.5 7B Instruct on OpenRouter

Lyria 3 Pro Preview vs Qwen2.5 7B Instruct

Live catalog fields. Best-in-row is highlighted.

Lyria 3 Pro Preview

Google · google__lyria-3-pro-preview

Qwen2.5 7B Instructopen

Qwen · qwen__qwen-2.5-7b-instruct

Identity

Fieldgoogle__lyria-3-pro-previewqwen__qwen-2.5-7b-instruct
ProviderGoogleQwen
Sluggoogle__lyria-3-pro-previewqwen__qwen-2.5-7b-instruct
Statuslivelive
Open weightsNoYes
License——
HuggingFace—Qwen/Qwen2.5-7B-Instruct

Quality

Fieldgoogle__lyria-3-pro-previewqwen__qwen-2.5-7b-instruct
Quality index (0–100)——

Cost

Fieldgoogle__lyria-3-pro-previewqwen__qwen-2.5-7b-instruct
Input $ / 1M tokens$0.00$0.10
Cached input $ / 1M——
Output $ / 1M tokens$0.00$0.20

Context

Fieldgoogle__lyria-3-pro-previewqwen__qwen-2.5-7b-instruct
Max context tokens1,048,57632,768
Max output tokens65,53629,491

Modalities

Fieldgoogle__lyria-3-pro-previewqwen__qwen-2.5-7b-instruct
Inputtext, imagetext
Outputtext, audiotext