Benchmark
LiveCodeBench Pro Medium
Coding benchmarks compare models on programming tasks. Scores are percentages.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.51
Score distribution
- 21.8%
- Mean
- 29.2%
- Median
- 20.2%
- Std dev
- 1.4%
- 10th percentile
- 52.1%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 0.51 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 5.2Medium· LiveCodeBench Pro data | 52.1% |
| 2 | GPT 5Medium, high· LiveCodeBench Pro data | 40.9% |
| 3 | o4 MiniMedium· LiveCodeBench Pro data | 29.2% |
| 4 | Qwen3 Next 80B A3BMedium, thinking· LiveCodeBench Pro data | 7% |
| 5 | DeepSeek R1Medium· LiveCodeBench Pro data | 1.4% |
| 6 | Claude Sonnet 4.5Medium, thinking· LiveCodeBench Pro data | 0% |