Python-Code-33B: 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. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1346 ± 33, rank #7799 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 81.01 | Normalized accuracy (%) (10-shot) | 43.3 |
| Open LLM Leaderboard v1 - WinoGrande | 75.22 | Accuracy (%) (5-shot) | 40.9 |
| Open LLM Leaderboard v1 - GSM8K | 19.18 | Accuracy (%) (5-shot) | 40.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.31 | Normalized accuracy (%) (25-shot) | 35.2 |
| Open LLM Leaderboard v1 - MMLU | 54.22 | Accuracy (%) (5-shot) | 33.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.39 | MC2 (%) (0-shot) | 27 |
Interactive version: theaggregate.ai/model?slug=python-code-33b · How It Works · Data refreshed daily, snapshot 2026-11-08.