MemLens (128K) - Information Extraction: leaderboard
Accuracy in percent on the MemLens 246 questions that extract a fact or image detail from one earlier session, at a 128K-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 information extraction (IE, 246 questions) at a 128K-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 February 2027. 25 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 60.16 | #138 |
| 2 | Qwen 3 VL 30B A3B Instruct | 56.5 | #903 |
| 3 | Gemini 3.1 Pro (Preview) | 55.79 | #102 |
| 4 | Qwen 3.5 27B | 54.07 | #380 |
| 5 | GLM-4.6V | 52.85 | #721 |
| 6 | Kimi K2.5 | 51.63 | #272 |
| 7 | Qwen 3 VL 235B A22B Instruct | 51.22 | #541 |
| 8 | Qwen 3.5 9B | 45.12 | #838 |
| 9 | Qwen 3.5 122B A10B | 43.09 | #350 |
| 10 | Cosmos-Reason2-8B | 36.99 | #758 |
| 11 | Qwen 3 VL 30B A3B (Thinking) | 33.74 | #727 |
| 12 | Qwen 3 VL 8B (Thinking) | 33.33 | #924 |
| 13 | Qwen 3 VL 8B Instruct | 32.52 | #1043 |
| 14 | Qwen 3.5 4B | 29.67 | #1270 |
| 15 | Qwen 3 VL 235B A22B (Thinking) | 29.27 | #462 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=memlens-128k-information-extraction · How It Works · Data refreshed daily, snapshot 2026-11-22.