Local Code Arena MBPP Qwen3 8B: Benchmark Telemetry for Code Generation

Raw evaluation metrics and execution telemetry logs from running the Mostly Basic Python Problems (MBPP) benchmark against the Qwen3 8B dense foundation model. The dataset documents zero-shot functional programming synthesis performance under standard local execution bounds. It was authored by ShahzebKhoso and last updated on May 29, 2026.

Use Cases

• Analyze code generation model performance based on benchmark evaluation metrics
• Study execution telemetry for model inference under local bounds
• Compare zero-shot functional programming synthesis results across different models
• Investigate structural syntax outputs from code generation tasks

Strengths

• Captures raw evaluation metrics from a standardized benchmark (MBPP)
• Includes execution telemetry logs for model inference analysis
• Documents performance of a specific 8-billion parameter model (Qwen3 8B)

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

huggingface

Collection Method

Likely contains telemetry from running the MBPP benchmark against the Qwen3 8B model.

Freshness

Last updated 2026-05-29 06:18:54