M3Exam (Multimodal Memory) - Thematic Reasoning: leaderboard
Metric: LLM-judge score (0-100) on the thematic reasoning (TH) questions of 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; scored by a Qwen2.5-VL-32B-Instruct judge on a five-level rubric (0, 0.25, 0.5, 0.75, 1), printed 0-1 and x100 here; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.1 | 61.93 |
| 2 | Claude Opus 4.6 | 60.83 |
| 3 | Qwen 3.6 Plus | 52.27 |
| 4 | Gemini 3.1 Pro (Preview) | 44.17 |
| 5 | Kimi K2.5 | 43.51 |
| 6 | GPT-5.4 | 43.33 |
| 7 | Grok 4 | 36.67 |
| 8 | Seed 2.0 Pro | 13.64 |
| 9 | Qwen 2.5 VL 7B Instruct | 6.35 |
Interactive version: theaggregate.ai/benchmark?slug=m3exam-multimodal-memory-thematic-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.