Local Code Arena Starcoder2 7B: MBPP Benchmark Telemetry

Raw evaluation metrics, execution telemetry logs, and structural syntax outputs from running the Mostly Basic Python Problems (MBPP) benchmark against the StarCoder2 7B base model. The dataset documents behavioral dynamics of mid-tier foundational weights in automated conversational evaluation workflows. It was authored by ShahzebKhoso and last updated on May 28, 2026.

Use Cases

• Analyze model performance on basic Python problems based on the MBPP benchmark results.
• Study execution telemetry and behavioral dynamics of foundational models mentioned in the description.
• Compare structural syntax outputs from automated conversational evaluation workflows.
• Benchmark the StarCoder2 7B model against other code generation models.

Strengths

• Captures raw evaluation metrics, execution telemetry logs, and structural syntax outputs.
• Documents behavioral dynamics of a modern, mid-tier foundational model (StarCoder2 7B).
• Focuses on a standardized benchmark (Mostly Basic Python Problems).

Limitations

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

Provenance

Source

huggingface

Collection Method

Telemetry captured from running the MBPP benchmark against the StarCoder2 7B model.

Freshness

Last updated 2026-05-28 13:38:13; freshness should be verified.