MMShopBench - Identifier Match@3: leaderboard

Metric: Identifier match at 3 (%; share of cases in which any of the first three recommended products is one of the human-verified target product identifiers; multimodal multi-turn shopping requests from real assistant logs, answered by a tool-using agent over a frozen offline catalog with text and region-aware image retrieval (at most eight tool steps), followed by evidence-grounded verification and selection of the candidate pool by the policy model). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)64
2Claude Opus 4.8 (Thinking)59.9
3Kimi K2.6 (Thinking)38.8
4MiniMax-M2.721.5
5Qwen 3.5 9B (Non-reasoning)19.4
6Qwen 3.5 27B (Non-reasoning)11.4
7Qwen 3.5 122B A10B (Non-reasoning)5.9

Interactive version: theaggregate.ai/benchmark?slug=mmshopbench-identifier-match-3 · How It Works · Data refreshed daily, snapshot 2026-09-29.