MemLens (64K) - Multi-Session Reasoning: leaderboard
Accuracy in percent on the MemLens 143 questions that combine evidence from several sessions, at a 64K-token interleaved image and text conversation history, with the evidence sessions hidden among distractor sessions (MemLens, 2026), judged by Qwen3-VL-235B. Higher is better.
Metric: Accuracy (%) on the multi-session reasoning (MSR, 143 questions) at a 64K-token history, interleaved multimodal multi-session conversation history with the evidence sessions hidden among haystack sessions, judged correct or incorrect by a Qwen3-VL-235B-A22B-Instruct judge; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 27 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.5 | 35.66 | #266 |
| 2 | Gemini 3.1 Pro (Preview) | 31.47 | #99 |
| 3 | GPT-5.4 | 27.27 | #135 |
| 4 | Qwen 3.5 122B A10B | 27.27 | #346 |
| 5 | GLM-4.6V | 23.78 | #710 |
| 6 | Gemma 3 27B (IT) | 22.38 | #1324 |
| 7 | Gemma 3 12B (IT) | 22.38 | #1887 |
| 8 | Qwen 3 VL 2B Instruct | 21.68 | #2367 |
| 9 | Qwen 3.5 27B | 20.98 | #375 |
| 10 | Qwen 3 VL 235B A22B Instruct | 20.98 | #532 |
| 11 | Phi-4 Multimodal Instruct | 20.98 | #4154 |
| 12 | Nemotron Nano 12B v2 VL | 20.98 | #2368 |
| 13 | Qwen 3 VL 30B A3B Instruct | 20.28 | #895 |
| 14 | Cosmos-Reason2-8B | 20.28 | #755 |
| 15 | Qwen 3 VL 8B Instruct | 19.58 | #1029 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=memlens-64k-multi-session-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.