AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
HumanEval
Saturated. Retained because open-weight cards still report it.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2021-07-07
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 2
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Gemini 1.5 Pro | 84.1 | percent | 0-shot, chat preamble | 2024-03-08 · document_publication | Gemini 1.5 |
| Qwen2.5-Coder-32B-Instruct | 92.7 | percent | HumanEval base split | 2024-09-18 · document_publication | Qwen2.5-Coder |