MemLens (64K) - Temporal Reasoning: leaderboard
Accuracy in percent on the MemLens 194 questions about dates, durations and the order of events, 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 temporal reasoning (TR, 194 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 May 2028. 27 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 30B A3B Instruct | 55.15 | #903 |
| 2 | Qwen 3 VL 235B A22B Instruct | 54.12 | #541 |
| 3 | GLM-4.6V | 53.09 | #721 |
| 4 | Kimi K2.5 | 52.06 | #272 |
| 5 | Qwen 3.5 122B A10B | 51.55 | #350 |
| 6 | Qwen 3 VL 8B (Thinking) | 50.52 | #924 |
| 7 | Qwen 3 VL 8B Instruct | 47.42 | #1043 |
| 8 | Cosmos-Reason2-8B | 45.88 | #758 |
| 9 | Gemma 3 27B (IT) | 44.33 | #1341 |
| 10 | Gemma 3 12B (IT) | 44.33 | #1907 |
| 11 | Qwen 3 VL 235B A22B (Thinking) | 42.78 | #462 |
| 12 | Nemotron Nano 12B v2 VL | 42.78 | #2385 |
| 13 | Gemini 3.1 Pro (Preview) | 42.27 | #102 |
| 14 | GPT-5.4 | 42.27 | #138 |
| 15 | Qwen 3 VL 2B Instruct | 40.72 | #2389 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=memlens-64k-temporal-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-22.