Engram - Llama3.1-8b-Insturct - HotpotQA F1: leaderboard
Engram v1 A3.T6.7.2, native task performance (%), full reported method roster. Student backbone Llama3.1-8b-Insturct; trained adapters and memory frameworks remain native run configurations, not released-model aliases. Full table and confidence intervals retained; no resource, conditional verification or retention rate admitted.
Metric: Accuracy / task score (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama3.1-8b-Insturct (Engram Run: method=Engram;effort=source-unreported) | 65.8 | |
| 2 | Llama3.1-8b-Insturct (Engram Run: method=EmbQA;effort=source-unreported) | 61 | |
| 3 | Llama3.1-8b-Insturct (Engram Run: method=RoleRAG;effort=source-unreported) | 60.2 | |
| 4 | Llama3.1-8b-Insturct (Engram Run: method=EvolveR;effort=source-unreported) | 58.7 | |
| 5 | Llama3.1-8b-Insturct (Engram Run: method=SuRe;effort=source-unreported) | 55.8 | |
| 6 | Llama3.1-8b-Insturct (Engram Run: method=RPG;effort=source-unreported) | 53.9 | |
| 7 | Llama3.1-8b-Insturct (Engram Run: method=ReAct;effort=source-unreported) | 49.8 | |
| 8 | Llama3.1-8b-Insturct (Engram Run: method=CoT;effort=source-unreported) | 47.6 |
Interactive version: theaggregate.ai/benchmark?slug=engram-llama3-1-8b-insturct-hotpotqa-f1 · How It Works · Data refreshed daily, snapshot 2026-11-12.