Benchmark
LiveCodeBench v5
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from…
- Modality
- text
- Categories
- reasoning, general
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 9
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 2.0 Flash-Lite | 0.289 | 2025-02-05 | evidence | |
| Gemini 2.5 Flash | 0.639 | 2025-05-20 | evidence | |
| Gemini 2.5 Pro | 0.756 | 2025-05-20 | evidence | |
| Gemma 3n E2B Instructed | 0.186 | 2025-06-26 | evidence | |
| Gemma 3n E2B Instructed LiteRT (Preview) | 0.186 | 2025-05-20 | evidence | |
| Gemma 3n E4B Instructed | 0.257 | 2025-06-26 | evidence | |
| Gemma 3n E4B Instructed LiteRT Preview | 0.257 | 2025-05-20 | evidence | |
| MiniCPM-SALA | OpenBMB | 0.6048 | 2026-02-11 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.614 | 2025-09-22 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.