RankingLiveCodeBench
LiveCodeBench
- Bucket
- Coding
- Unit
- percent
- Direction
- Higher is better
- Version
- v6
- Display harness
- LiveCodeBench pass@1
- Board
- https://livecodebench.github.io/
Compare published benchmark results with category weights →
Models
1–25 of 471 entries
| Model | Score | Evidence | Source-recorded date |
|---|---|---|---|
| DeepSeek V4-Pro 0813DeepSeek | 93.5% | lab self-report | 2026-08-13 |
| NVIDIA Nemotron 3 UltraNVIDIA | 89% | lab self-report | 2026-06-04 |
| o4-miniOpenAI | 80.2% | official board | 2025-05-01 |
| o3OpenAI | 75.8% | official board | 2025-05-01 |
| DeepSeek-R1-0528DeepSeek | 73.1% | official board | 2025-05-01 |
| EXAONE 4.0 32BLG AI Research | 70% | official board | 2025-05-01 |
| o3-miniOpenAI | 67.4% | official board | 2025-05-01 |
| Qwen3-235B-A22BQwen | 65.9% | official board | 2025-05-01 |
| Llama 4 MaverickMeta | 43.4% | lab self-report | 2025-04-05 |
| GPT-4oOpenAI | 29.5% | official board | 2025-05-01 |
| GPT-4-turboOpenAI | 28.7% | official board | 2025-05-01 |
| GPT-4o MiniOpenAI | 27.5% | official board | 2025-05-01 |
| Agnes 2.5 Pro AlphaAgnes AI | — | — | — |
| Agnes-3.0-Flash PreviewAgnes AI | — | — | — |
| Amazon Nova 2 LiteAmazon | — | — | — |
| Amazon Nova 2 Pro PreviewAmazon | — | — | — |
| Amazon Nova LiteAmazon | — | — | — |
| Amazon Nova MicroAmazon | — | — | — |
| Amazon Nova PremierAmazon | — | — | — |
| Amazon Nova ProAmazon | — | — | — |
| AutoGLM-Phone-9BZ.ai | — | — | — |
| AutoGLM-Phone-9B-MultilingualZ.ai | — | — | — |
| aya-101Cohere | — | — | — |
| aya-23-35BCohere | — | — | — |
| aya-23-8BCohere | — | — | — |