Python-Code-13B: benchmark results
A coding fine-tune by ajibawa-2023 on over 23,000 Python conversation sets in Vicuna/ShareGPT format, using the Python-Code-23k-ShareGPT dataset. The card identifies Llama-2 as its base. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1337 ± 34, rank #8026 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 81.66 | Normalized accuracy (%) (10-shot) | 46.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.79 | Normalized accuracy (%) (25-shot) | 40.9 |
| Open LLM Leaderboard v1 - MMLU | 54.78 | Accuracy (%) (5-shot) | 34.6 |
| Open LLM Leaderboard v1 - WinoGrande | 74.03 | Accuracy (%) (5-shot) | 34.6 |
| Open LLM Leaderboard v1 - GSM8K | 9.55 | Accuracy (%) (5-shot) | 30.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.83 | MC2 (%) (0-shot) | 21.7 |
| EvalPlus (HumanEval+ & MBPP+) | 30.5 | Pass@1 avg (%) | 20.2 |
Interactive version: theaggregate.ai/model?slug=python-code-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.