VOLTBench - Mean Length Accuracy (10 Sections): leaderboard
Length adherence on VOLTBench (2026), a long-form generation benchmark of chapter-based story and code instructions, at the 10-section target: five generations are sampled per instruction and their mean length is scored as 100 x max(0, 1 - |mean - target| / target). Percent; higher is better.
Metric: Mean length accuracy (%): 100 x max(0, 1 - |mean output length - target length| / target length) over the five sampled generations per instruction, English simple-difficulty instructions, Story (unstructured) and Code Function (structured) chapter-based tasks, 10-section target; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | LongWriter-8B | 68.7 | |
| 2 | DeepSeek R1 | 61 | #482 |
| 3 | GPT-4o Mini | 53.3 | #1667 |
| 4 | DeepSeek V3 | 41.4 | #729 |
| 5 | Qwen 2.5 7B Instruct | 37.2 | #2723 |
| 6 | Claude 3.5 Sonnet | 34.8 | #752 |
| 7 | Qwen 2.5 1.5B Instruct | 32.8 | #7470 |
| 8 | Llama 3.1 8B Instruct | 32.5 | #4600 |
| 9 | Falcon3-Mamba-7B-Instruct | 30.4 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=voltbench-mean-length-accuracy-10-sections · How It Works · Data refreshed daily, snapshot 2026-11-21.