Letta Memory Benchmark - Core Memory Read: leaderboard
The Letta agent answers from facts held in its in-context core memory block, over 100 items repeated 3 times; the score is the share answered correctly. Unlike the archival read task, the facts are already in context.
Metric: Score (%) on 100 core-memory read items, 3 repeats, Letta agent framework. Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 18 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-4o (2024-08-06) | 100 | #736 | |
| 2 | O4 Mini | 100 | #356 | |
| 3 | Claude Sonnet 4 (20250514) | 100 | #388 | |
| 4 | O3 Mini | 100 | #544 | |
| 5 | Gemini 2.5 Pro (Preview 05-06) | 100 | #279 | |
| 6 | GPT-4.1 Mini | 99.67 | #781 | |
| 7 | GPT-4o Mini (2024-07-18) | 99.67 | #1511 | |
| 8 | Gemini 2.5 Flash (Preview 05-20) | 99.67 | #423 | |
| 9 | Claude 3.7 Sonnet (20250219) | 99 | #414 | |
| 10 | Claude Sonnet 4 | Thinking | 97.67 | #406 |
| 11 | Llama 3.3 70B Instruct | 97 | #1379 | |
| 12 | Llama 4 Maverick Instruct FP8 | 92.33 | #1010 | |
| 13 | Claude 3.5 Haiku (20241022) | 62 | #1601 | |
| 14 | Gemini 2.5 Flash (Preview 04-17) | 37.67 | #458 | |
| 15 | Llama 4 Scout Instruct | 31.33 | #1579 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=letta-memory-benchmark-core-memory-read · How It Works · Data refreshed daily, snapshot 2026-11-16.