Benchmark
LiveCodeBench
What is LiveCodeBench?
Time-sliced problem set. A score without its problem window is not comparable to any other score. Benchmark Radar tracks 15 reported scores for LiveCodeBench…
- Released
- 2024-03-12
- Evaluates
- coding
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 15
Source provenance
- Original evidence https://livecodebench.github.io/
LiveCodeBench links
- Website https://livecodebench.github.io/
LiveCodeBench results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-R1 | DeepSeek | 65.9 | 2025-01-22 | evidence |
| DeepSeek-V3 | DeepSeek | 37.6 | 2024-12-27 | evidence |
| DeepSeek-V3 | DeepSeek | 40.5 | 2024-12-27 | evidence |
| DeepSeek-V4-Flash | DeepSeek | 91.6 | 2026-06-25 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 56.8 | 2026-04-22 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 89.8 | 2026-04-22 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 93.5 | 2026-04-22 | evidence |
| Gemini 2.5 Pro | 74.2 | 2025-06-17 | evidence | |
| Gemma 4 (31B) | 80.0 | 2026-03-11 | evidence | |
| Qwen2.5-Coder-32B-Instruct | Qwen | 31.4 | 2024-09-18 | evidence |
| Qwen3-235B-A22B (Thinking) | Qwen | 70.7 | 2025-05-14 | evidence |
| Qwen3.5-397B-A17B | Qwen | 83.6 | 2026-02-16 | evidence |
| Seed2.0 Lite | ByteDance | 67.5 | 2026-02-14 | evidence |
| Seed2.0 Mini | ByteDance | 57.8 | 2026-02-14 | evidence |
| Seed2.0 Pro | ByteDance | 87.8 | 2026-02-14 | 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.
Which sources cite LiveCodeBench?
- Qwen3.8-27B Qwen, 2026-08-05
- DeepSeek-V4 DeepSeek, 2026-06-25
- DeepSeek-V4-Pro DeepSeek, 2026-04-22
- Gemma 4 (31B) Google, 2026-03-11
- Qwen3.5-397B-A17B Qwen, 2026-02-16
- Seed2.0 (Pro / Lite / Mini) ByteDance, 2026-02-14
- Mistral Large 3 (675B) Mistral, 2025-11-28
- Olmo 3 (7B and 32B) Ai2, 2025-11-20
- GPT-5 OpenAI, 2025-08-07
- Grok 4 xAI, 2025-07-09
- Gemini 2.5 Pro Google, 2025-06-17
- Qwen3 Qwen, 2025-05-14
18 source documents cite this benchmark.