tencent/autocodebench
Coding
Multilingual automated code generation benchmark evaluating LLMs across diverse programming tasks and languages.
Run this task
CLI:
inspect eval inspect_harbor/tencent_autocodebench --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import tencent_autocodebench
eval(tencent_autocodebench(), model="openai/gpt-5")Dataset information
| Harbor registry | tencent/autocodebench |
| Inspect task | tencent_autocodebench |
| Latest digest | sha256:da30a5e97eeccc2d024a2ff947fb99966ea88bed5b7077ee451d2ae72e645caf |
| Samples | 200 |
| Paper | arxiv |
| Source | https://github.com/Tencent-Hunyuan/AutoCodeBenchmark |
See Task Parameters for the parameter set shared across all Harbor tasks.