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
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.1 | 54.93 |
| 2 | Qwen 3.6 Plus | 50.49 |
| 3 | Seed 2.0 Pro | 49.38 |
| 4 | Claude Opus 4.6 | 49.37 |
| 5 | GPT-5.4 | 48.23 |
| 6 | Gemini 3.1 Pro (Preview) | 46.68 |
| 7 | Kimi K2.5 | 44.93 |
| 8 | Grok 4 | 43.57 |
| 9 | Qwen 2.5 VL 7B Instruct | 41.79 |
Interactive version: theaggregate.ai/benchmark?slug=m3exam-multimodal-memory · How It Works · Data refreshed daily, snapshot 2026-09-29.