Benchmark
HumanEval-Mul
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
All coding benchmarksScores from LLM Stats data.
- Models measured
- 2
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 78.2%
- Mean
- 82.6%
- Median
- 4.4%
- Std dev
- 73.8%
- 10th percentile
- 82.6%
- 90th percentile
- 73.8%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.6% |
| 2 | DeepSeek V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.8% |
Data credits: Data by LLM Stats