Benchmark
Natural2Code Benchmark
What is Natural2Code?
NaturalCodeBench (NCB) is a challenging code benchmark designed to mirror the complexity and variety of real-world coding tasks. It comprises 402 high-quality…
- Modality
- text
- Evaluates
- reasoning, general
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 8
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/natural2code?top_n=500
Natural2Code results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 1.5 Flash | 0.798 | 2024-05-01 | evidence | |
| Gemini 1.5 Flash 8B | 0.755 | 2024-03-15 | evidence | |
| Gemini 1.5 Pro | 0.854 | 2024-05-01 | evidence | |
| Gemini 2.0 Flash | 0.929 | 2024-12-01 | evidence | |
| Gemma 3 12B | 0.807 | 2025-03-12 | evidence | |
| Gemma 3 1B | 0.56 | 2025-03-12 | evidence | |
| Gemma 3 27B | 0.845 | 2025-03-12 | evidence | |
| Gemma 3 4B | 0.703 | 2025-03-12 | 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.