HEART-Bench - PersonaDB: leaderboard
HEART-Bench (2026) tests whether LLM agents can act like a specific person: given only retrieved memories of one of 11 Big Five-grounded characters, the model picks which of four options that character would choose, over 673 expert-validated scenario decisions. This board is accuracy in percent when memories are organized by the PersonaDB persona-structured framework (chance 25); higher is better.
Metric: Accuracy (%) with the PersonaDB persona-structured memory framework, times 100, 673 four-option multiple-choice questions on what one of 11 Big Five-grounded characters would do in a scenario, the prompt exposing only the character ID, occupation and retrieved de-identified episodic memories (Qwen3-Embedding-4B retriever, GPT-5.4-mini auxiliary memory manager); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 62.4 | #99 |
| 2 | Gemini 3 Flash | 52.5 | #175 |
| 3 | DeepSeek V3.2 | 42.8 | #419 |
| 4 | Qwen 3.5 397B A17B | 40.4 | #264 |
| 5 | Claude Sonnet 4.6 | 40.1 | #173 |
| 6 | Qwen 3.5 122B A10B | 38.9 | #346 |
| 7 | Claude Haiku 4.5 | 37.6 | #583 |
| 8 | DeepSeek V4 Pro | 36.7 | #196 |
| 9 | Qwen 3.5 35B A3B | 36.6 | #492 |
| 10 | GPT-5.4 | 35.1 | #135 |
| 11 | DeepSeek V4 Flash | 32.8 | #267 |
| 12 | GPT-5.4 Mini | 32.2 | #406 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=heart-bench-personadb · How It Works · Data refreshed daily, snapshot 2026-11-21.