LiveBench Math Comp — leaderboard
Metric: Score. Source: livebench.ai. 73 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro (Preview 0827) | 54.17 |
| 2 | DeepSeek V2.5 | 53.12 |
| 3 | DeepSeek Coder V2 | 50 |
| 4 | GPT-4o (2024-08-06) | 47.92 |
| 5 | Claude 3.5 Sonnet (20240620) | 44.79 |
| 6 | GPT-4o ChatGPT | 44.79 |
| 7 | GPT-4 Turbo | 44.79 |
| 8 | Llama 3.1 70B Instruct | 41.67 |
| 9 | Claude 3 Opus (20240229) | 41.67 |
| 10 | GPT-4o (2024-05-13) | 39.58 |
| 11 | Qwen 2 72B Instruct | 37.5 |
| 12 | Llama 3.1 405B Instruct | 37.5 |
| 13 | Gemini 1.5 Pro (Preview 0801) | 37.5 |
| 14 | GPT-4 Preview (0125) | 36.46 |
| 15 | Gemini 1.5 Pro (0514) | 36.46 |
Interactive version: theaggregate.ai/benchmark?slug=livebench-math-comp · How the rankings work · Data refreshed daily, snapshot 2026-07-22.