Project AURIONAI Use-Cases Research & Innovation
Retail and Logistics

Product Catalogue Content Generation and Data Quality

Writes product descriptions from images and specifications and fixes errors in product data.

Named Models

The research names no model for this use case.

Where this comes from
Models the research names for this use case. Research, with sources on each model record.

Who Runs It

production, 1
PT TokopediaTokopediaCountry: IndonesiaVertex AI to improve product data qualityVendor: Google CloudproductionDate–Unique products sold up 5 percent (claim)Evidence: company statementConfidence: lowSource: cloud.google.com
Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.

Candidate Models

Artificial Analysis Intelligence Index: AA leaderboard, 205 current models

A general benchmark for this model class, not a test on this use case. Composite intelligence score across AA evaluations. index. Higher is better. Showing 10 of 30.

AnthropicClaude Opus 5.5Anthropic independent58AnthropicClaude Sonnet 5.5Anthropic independent56AnthropicClaude Fable 5.1Anthropic independent53Google DeepMindGemini 4 ArgonGoogle DeepMind independent53OpenAIGPT-6 AstraOpenAI independent53OpenAIGPT-6.1 SolOpenAI independent52MetaMuse Spark 1.3Meta independent48SpaceXAI (xAI)Grok 4.7SpaceXAI (xAI) independent46XiaomiMiMo-V2.6-ProXiaomi independent46Alibaba (Qwen)Qwen3.8 MaxAlibaba (Qwen) independent45
050100
AI SingaporeNemotron-SEA-LION-v4.8-120B-A12BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsAI SingaporeNemotron-SEA-LION-v4.8-30B-A3BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsSwiss AI (EPFL, ETH Zurich, CSCS)Apertus v1.5 70BSwiss AI (EPFL, ETH Zurich, CSCS), multimodal LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsMetaMuse Glimmer 30BMeta, multimodal LLMReleasedAug 2026open weightsIndonesian statedhas scoreslast 18 monthsAI SingaporeQwen-SEA-LION-v4.5-27B-ITAI Singapore, LLMReleasedMay 2026open weightsIndonesian statedhas scoreslast 18 monthsMistral AIMistral Medium 3.5 (v26.04)Mistral AI, multimodal LLMReleasedApr 2026open weightsIndonesian statedhas scoreslast 18 monthsGoogleGemma 4 31BGoogle, Google DeepMind, multimodal LLMReleasedApr 2026open weightsIndonesian statedhas scoreslast 18 monthsAlibaba (Qwen)Qwen3.6-35B-A3BAlibaba (Qwen), LLMReleasedApr 2026open weightsruns on edgehas scoreslast 18 monthsAlibaba (Qwen)Qwen3.6-27BAlibaba (Qwen), multimodal LLMReleasedApr 2026open weightsIndonesian statedhas scoreslast 18 monthsAlibaba (Qwen)Qwen3.5-4BAlibaba (Qwen), multimodal LLMReleasedMar 2026open weightsruns on edgehas scoreslast 18 months

Showing 10 of 585. All models of this class

Where this comes from
Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.

Sources

  1. cloud.google.com/transform/101-real-world-generative-ai-use-ca... https://cloud.google.com/transform/101-real-world-generative-ai-use-cases-from-industry-leaders

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Product Catalogue Content Generation and Data Quality", https://aurion.semai.id/usecases/ret-catalogue-content-quality/, records of October 2026.