LiveBench Summarize — leaderboard
Metric: Score. Source: livebench.ai. 73 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B Instruct | 83.85 |
| 2 | Gemini 1.5 Pro (Preview 0801) | 83.13 |
| 3 | Llama 3.1 405B Instruct | 78.93 |
| 4 | GPT-4o (2024-08-06) | 75.78 |
| 5 | GPT-4o (2024-05-13) | 74.62 |
| 6 | Gemini 1.5 Pro (Preview 0827) | 73.4 |
| 7 | GPT-4 (0613) | 73.33 |
| 8 | Gemini 1.5 Flash (Preview 0827) | 72.77 |
| 9 | GPT-4o ChatGPT | 71.42 |
| 10 | Claude 3 Opus (20240229) | 70.48 |
| 11 | Claude 3 Haiku (20240307) | 69.58 |
| 12 | Mistral Large | 69.23 |
| 13 | Claude 3.5 Sonnet (20240620) | 68.88 |
| 14 | Mistral Large 2 (Jul) | 68.15 |
| 15 | GPT-4 Turbo | 67.6 |
Interactive version: theaggregate.ai/benchmark?slug=livebench-summarize · How the rankings work · Data refreshed daily, snapshot 2026-07-22.