LiveBench Story Generation — leaderboard
Metric: Score. Source: livebench.ai. 73 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Flash (Preview 0827) | 81.33 |
| 2 | Command-R+ | 80.83 |
| 3 | Qwen 2 72B Instruct | 80.17 |
| 4 | GPT-4o (2024-08-06) | 80.08 |
| 5 | GPT-4o ChatGPT | 79.92 |
| 6 | GPT-4 Turbo | 79.92 |
| 7 | Mistral Large 2 (Jul) | 78.5 |
| 8 | DeepSeek V2.5 | 77.17 |
| 9 | Gemini 1.5 Pro (Preview 0801) | 77.08 |
| 10 | GPT-4 (0613) | 76.08 |
| 11 | Llama 3.1 405B Instruct | 75.5 |
| 12 | Llama 3.1 70B Instruct | 75.42 |
| 13 | DeepSeek Coder V2 | 75.33 |
| 14 | Gemini 1.5 Pro (Preview 0827) | 75 |
| 15 | Claude 3.5 Sonnet (20240620) | 74.33 |
Interactive version: theaggregate.ai/benchmark?slug=livebench-story-generation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.