Local Code Arena MBPP Starcoder 1B: Benchmark Telemetry for a Code Model

Local Code Arena Telemetry: MBPP Benchmark on StarCoder 1B (Base) hosts raw evaluation metrics, execution telemetry logs, and structural syntax outputs. The data was captured from running the Mostly Basic Python Problems (MBPP) benchmark against the StarCoder 1B base model. It was authored by ShahzebKhoso and last updated on 2026-05-24.

Use Cases

• Analyzing inference speed and hardware performance based on execution telemetry logs.
• Evaluating functional limitations of unaligned base models based on benchmark results.
• Comparing raw model outputs against expected solutions based on structural syntax data.

Strengths

• Includes raw evaluation metrics from a standardized benchmark (MBPP).
• Contains execution telemetry logs providing hardware performance data.
• Captures structural syntax outputs for model output analysis.

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 and file formats are unknown, which may limit suitability assessment.

Provenance

Source

ShahzebKhoso via Hugging Face.

Collection Method

Telemetry captured from running the MBPP benchmark on the StarCoder 1B model.

Freshness

Last updated 2026-05-24 11:39:48; freshness should be verified.