Code-290k-13B: benchmark results
A full Llama-2 fine-tune by ajibawa-2023 on approximately 290,000 coding conversation sets, using the Code-290k-ShareGPT dataset. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1333 ± 34, rank #8109 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 81.55 | Normalized accuracy (%) (10-shot) | 45.7 |
| Open LLM Leaderboard v1 - GSM8K | 17.82 | Accuracy (%) (5-shot) | 39.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.06 | Normalized accuracy (%) (25-shot) | 34.7 |
| Open LLM Leaderboard v1 - MMLU | 51.99 | Accuracy (%) (5-shot) | 31.3 |
| Open LLM Leaderboard v1 - WinoGrande | 72.69 | Accuracy (%) (5-shot) | 29.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.65 | MC2 (%) (0-shot) | 6.4 |
Interactive version: theaggregate.ai/model?slug=code-290k-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.