AspectSim (Summarize-Then-Embed): leaderboard
Metric: Spearman correlation (-1 to 1) between the embedding similarity of the evidence the LLM extracts from each document and the GPT-4o aspect-similarity labels, mean over nine embedding models; the LLM writes an aspect-conditioned summary. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 0.57 |
| 2 | Phi-4 | 0.57 |
| 3 | Qwen 2.5 14B Instruct | 0.56 |
| 4 | Qwen 2.5 32B Instruct | 0.56 |
| 5 | Qwen 3 8B | 0.56 |
| 6 | DeepSeek R1 Distill Qwen 32B | 0.55 |
| 7 | Llama 3.3 70B Instruct | 0.54 |
| 8 | Gemma 3 12B (IT) | 0.53 |
| 9 | Qwen 3 4B | 0.52 |
| 10 | Gemma 2 27B (IT) | 0.52 |
| 11 | DeepSeek R1 Distill Qwen 14B | 0.48 |
| 12 | Mistral 7B Instruct | 0.47 |
| 13 | Llama 3.2 3B Instruct | 0.4 |
| 14 | Phi-4 Mini Instruct | 0.36 |
| 15 | Gemma 3 1B (IT) | 0.06 |
Interactive version: theaggregate.ai/benchmark?slug=aspectsim-summarize-then-embed · How It Works · Data refreshed daily, snapshot 2026-09-26.