benchmarks / livebench
LiveBench
score. Status active. Contamination risk low. Maintainer LiveBench / Epoch collection. Source.
| Model | Score | Date | Kind |
|---|---|---|---|
| Gemini 2.5 Pro Exp 03.25 | 82.35 | 2025-03-25 | observation |
| Claude 3.7 Sonnet | 76.1 | 2025-02-24 | observation |
| O3 Mini | 75.88 | 2025-01-31 | observation |
| O1 | 75.67 | 2024-12-17 | observation |
| Qwq 32B | 71.96 | 2025-03-05 | observation |
| DeepSeek R1 | 71.57 | 2025-01-20 | observation |
| O3 Mini | 70.01 | 2025-01-31 | observation |
| GPT-4.5 Preview | 68.95 | 2025-02-27 | observation |
| Gemini 2.0 Flash Thinking Exp 01.21 | 66.92 | 2025-01-21 | observation |
| DeepSeek V3 0324 | 66.86 | 2025-03-24 | observation |
| Gemini 2.0 Pro Exp 02.05 | 65.13 | 2025-02-05 | observation |
| Gemini Exp 1206 | 64.09 | 2024-12-06 | observation |
| O3 Mini | 62.45 | 2025-01-31 | observation |
| Qwen2 5 | 62.29 | 2025-01-28 | observation |
| Gemini 2.0 Flash 001 | 61.47 | 2025-02-05 | observation |
| DeepSeek V3 | 60.45 | 2024-12-26 | observation |
| Gemini 2.0 Flash Exp | 59.26 | 2024-12-11 | observation |
| Claude 3.5 Sonnet | 59.03 | 2024-10-22 | observation |
| O1 Mini | 57.76 | 2024-09-12 | observation |
| GPT-4O | 52.19 | 2024-11-20 | observation |
| DeepSeek R1 Distill Llama 70B | 54.5 | 2025-01-20 | observation |
| Grok 2 1212 | 54.3 | 2024-12-12 | observation |
| Gemini 2.0 Flash Lite | 54.29 | 2025-02-05 | observation |
| Gemini 2.0 Flash Lite Preview 02.05 | 53.24 | 2025-02-05 | observation |
| Dracarys2 72B Instruct | 52.64 | 2024-09-30 | observation |
| Llama 3.3 70B Instruct | 50.16 | 2024-12-06 | observation |
| Gemma 3 27B IT | 49.99 | 2025-03-12 | observation |
| Claude 3 Opus | 49.16 | 2024-02-29 | observation |
| Mistral Large 2411 | 48.43 | 2024-11-18 | observation |
| Qwen2 5 Coder 32B Instruct | 46.23 | 2024-11-21 | observation |