FrontierMemory1.0 Letta Dream memory model (best of two taskmodels at max): leaderboard
FrontierMemory1.0 Letta Dream memory model (best of two taskmodels at max) — Memory-generation model uses Letta Dream; Letta Code task agent uses Opus5.5 or GPT6Sol, native leaderboard publishes better of the two at max task effort.15tasks×3independent runs. This is not a same-model-agent score. Metric: Full pass rate (%). Source: https://www.frontiermemory.com/blog/v1/
Metric: Full pass rate (%). Source: www.frontiermemory.com. Saturation forecast: Around July 2028. 7 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Max | 73.3 | #5 |
| 2 | Kimi K3 | Max | 71.1 | #56 |
| 3 | GLM-5.3 | Max | 68.9 | #68 |
| 4 | Gemini 4 Argon | High | 64.4 | #12 |
| 5 | GPT-6.1 Sol | Max | 51.1 | #10 |
| 6 | Muse Wonder | xHigh | 51.1 | #28 |
| 7 | Grok 4.7 | xHigh | 37.8 | #47 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #6 GPT-6 Astra.
Interactive version: theaggregate.ai/benchmark?slug=frontiermemory1-0-letta-dream-memory-model-best-of-two-taskmodels-at-max · How It Works · Data refreshed daily, snapshot 2026-11-16.