Benchmark
BigCodeBench-Hard
What is BigCodeBench-Hard?
BigCodeBench-Hard is a subset of 148 challenging programming tasks from BigCodeBench, designed to evaluate large language models' ability to solve complex…
- Modality
- text
- Evaluates
- reasoning, general
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
BigCodeBench-Hard results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2.5-Coder 32B Instruct | Qwen | 0.27 | 2024-09-19 | 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.