reasoning benchmark
NaturalCodeBench (NCB) is a challenging code benchmark designed to mirror the complexity and variety of real-world coding tasks. It comprises 402 high-quality problems in Python and Java, selected from natural user queries from online coding services, covering 6 different domains.
Updated Aug 11, 2026
Higher score ranks better on this benchmark.
| 01 | GO | 92.9% | 100.0% | 8 | C | |
| 02 | GO | 85.4% | 85.7% | 8 | C | |
| 03 | GO | 84.5% | 71.4% | 8 | C | |
| 04 | GO | 80.7% | 57.1% | 8 | C | |
| 05 | GO | 79.8% | 42.9% | 8 | C | |
| 06 | GO | 75.5% | 28.6% | 8 | C | |
| 07 | GO | 70.3% | 14.3% | 8 | C | |
| 08 | GO | 56.0% | 0.0% | 8 | C |
A closer view of the leading scores on this benchmark.
The leading models and scores on this benchmark.
What Natural2Code measures and how its scores work.
NaturalCodeBench (NCB) is a challenging code benchmark designed to mirror the complexity and variety of real-world coding tasks. It comprises 402 high-quality problems in Python and Java, selected from natural user queries from online coding services, covering 6 different domains.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about Natural2Code.
Gemini 2.0 Flash is currently ranked first with 92.9%.
NaturalCodeBench (NCB) is a challenging code benchmark designed to mirror the complexity and variety of real-world coding tasks. It comprises 402 high-quality problems in Python and Java, selected from natural user queries from online coding services, covering 6 different domains.
Yes. Higher values rank better for this benchmark.
8 model results are currently shown.
Yes. This benchmark can contribute to the current LLMBoard capability score.