On Stable Long-Form Generation — leaderboard
Metric: LVC (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o Mini | 33.9 |
| 2 | Llama 3.1 8B | 26.5 |
| 3 | Qwen 2.5 7B | 17 |
| 4 | DeepSeek V3 | 2.2 |
| 5 | Claude 3.5 Sonnet | 1.9 |
Interactive version: theaggregate.ai/benchmark?slug=on-stable-long-form-generation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.