POLAR-Bench - Utility: leaderboard
The utility component of POLAR-Bench (2026): across 10 domains, an agent holding a document, a privacy policy and a task must still share the attributes the task needs with a questioning third-party model; the score is the share of task-relevant attributes shared. Percent; higher is better.
Metric: Utility score (%): share of the task-relevant attributes the model shared to complete the task, trusted agent holding a source document, a privacy policy and a task, questioned single-turn or multi-turn by a fixed Llama-3.3-70B-Instruct third party under five attack strategies, attributes revealed in the transcript extracted by normalization and regex, mean over the 10 domains; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 22 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.1 | 89.46 | #198 |
| 2 | Gemma 4 E2B | 87.56 | #4317 |
| 3 | Gemma 4 E4B | 86.29 | #2184 |
| 4 | GPT-5.4 | 84.79 | #135 |
| 5 | Gemma 3 27B | 84.71 | #1663 |
| 6 | Ministral 3 14B | 84.48 | #1870 |
| 7 | Qwen 3 32B | 84.43 | #972 |
| 8 | Ministral 3 8B | 83.7 | #2131 |
| 9 | DeepSeek R1 Distill Llama 70B | 82.93 | #1669 |
| 10 | Gemma 4 31B | 82.77 | #382 |
| 11 | DeepSeek V3.1 | 82.44 | #511 |
| 12 | Apertus-70B-Instruct-2509 | 81.8 | #2632 |
| 13 | Ministral 3 3B | 81.46 | #3504 |
| 14 | OLMo-3.1-32B | 80.02 | |
| 15 | SmolLM3-3B | 77.66 | #6555 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=polar-bench-utility · How It Works · Data refreshed daily, snapshot 2026-11-21.