LiveBench Simplify — leaderboard
Metric: Score. Source: livebench.ai. 73 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Flash (Preview 0827) | 84.75 |
| 2 | Llama 3.1 405B Instruct | 78.33 |
| 3 | Gemini 1.5 Pro (Preview 0827) | 77.8 |
| 4 | Gemini 1.5 Pro (Preview 0801) | 76.5 |
| 5 | Llama 3.1 70B Instruct | 74.8 |
| 6 | GPT-4 Turbo | 74.23 |
| 7 | Claude 3.5 Sonnet (20240620) | 73.77 |
| 8 | Mistral Large 2 (Jul) | 73.13 |
| 9 | Command-R+ | 72.63 |
| 10 | Claude 3 Opus (20240229) | 72.55 |
| 11 | GPT-4o (2024-08-06) | 72.38 |
| 12 | Gemini 1.5 Pro (0514) | 71.05 |
| 13 | GPT-4 (0613) | 70.97 |
| 14 | GPT-4o ChatGPT | 70.1 |
| 15 | GPT-4o (2024-05-13) | 69.6 |
Interactive version: theaggregate.ai/benchmark?slug=livebench-simplify · How the rankings work · Data refreshed daily, snapshot 2026-07-22.