VOLTBench - Structured Content Accuracy (50 Sections): leaderboard

Structured content accuracy on VOLTBench (2026) at the 50-section target: the share of the 50 required chapters of a generated code library that pass execution-based verification, averaged over five sampled generations. Percent; higher is better.

Metric: Structured content accuracy (%): share of the 50 required chapters of the Code Function task that pass execution-based verification, averaged over the five sampled generations per instruction, English simple-difficulty instructions, Story (unstructured) and Code Function (structured) chapter-based tasks; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1DeepSeek R199.6#482
2Llama 3.1 8B Instruct99.2#4600
3Qwen 2.5 7B Instruct98.8#2723
4DeepSeek V398.4#729
5Falcon3-Mamba-7B-Instruct91.2
6GPT-4o Mini79.6#1667
7LongWriter-8B71.6
8Qwen 2.5 1.5B Instruct29.2#7470
9Claude 3.5 Sonnet11.2#752

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=voltbench-structured-content-accuracy-50-sections · How It Works · Data refreshed daily, snapshot 2026-11-21.