M3Exam (Multimodal Memory): leaderboard

Metric: Overall Score (0-100): item-weighted composite with half weight on the LLM-judge score and the other half split over graded exact match, token F1 and BLEU-1, on 5,150 questions over 239 long multi-session user-assistant conversations with images and PDFs (15 personas); each model answers with the annotated gold supporting sessions and their images or rendered pages placed in context, no memory module; printed 0-1 and x100 here; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 9 models tracked.

Top models

#ModelScore
1GLM-5.154.93
2Qwen 3.6 Plus50.49
3Seed 2.0 Pro49.38
4Claude Opus 4.649.37
5GPT-5.448.23
6Gemini 3.1 Pro (Preview)46.68
7Kimi K2.544.93
8Grok 443.57
9Qwen 2.5 VL 7B Instruct41.79

Interactive version: theaggregate.ai/benchmark?slug=m3exam-multimodal-memory · How It Works · Data refreshed daily, snapshot 2026-09-29.