LiveCodeBench-v5
codingPending Verification
Evaluates models on their ability to solve coding problems in real-time.
Published: 2024
Score Range: 0-100
Top Score: 79.4
LiveCodeBench-v5 Leaderboard
| Rank | Model | Provider | Score | Parameters | Released | Type |
|---|---|---|---|---|---|---|
| 1 | Grok 4 | xAI | 79.4 | Unknown | 2025-07-09 | Multimodal |
| 2 | Gemini 2.5 Pro | 75.6 | 2025-05-06 | Multimodal | ||
| 3 | Qwen-3 | Alibaba | 70.7 | 235B (22B active) | 2025-04-29 | Text |
| 4 | Gemini 2.5 Flash | 63.9 | 2025-05-20 | Multimodal | ||
| 5 | Grok 3 | xAI | 57 | Unknown (multi-trillion estimated) | 2025-02-19 | Multimodal |
| 6 | Grok 3 Mini | xAI | 41.5 | Unknown | 2025-02-19 | Multimodal |
| 7 | Gemini 2.0 Pro | 36 | 2025-02-05 | Multimodal | ||
| 8 | Gemini 2.0 Flash | 34.5 | 2025-02-25 | Multimodal | ||
| 9 | Gemini 2.5 Flash-Lite | 34.3 | 2025-06-17 | Multimodal | ||
| 10 | Gemini 2.0 Flash-Lite | 28.9 | 2025-02-25 | Multimodal |
About LiveCodeBench-v5
Methodology
LiveCodeBench-v5 evaluates model performance using a standardized scoring methodology. Scores are reported on a scale of 0 to 100, where higher scores indicate better performance. For detailed information about the scoring system and methodology, please refer to the original paper.
Publication
This benchmark was published in 2024.Technical Paper