Code-13B: benchmark results
A full Llama-2 fine-tune by ajibawa-2023 on approximately 74,000 coding conversation sets with explanations, using Vicuna/ShareGPT format. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1346 ± 32, rank #7811 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 83.28 | Normalized accuracy (%) (10-shot) | 57.4 |
| EvalPlus (HumanEval+ & MBPP+) | 52.4 | Pass@1 avg (%) | 48.8 |
| Open LLM Leaderboard v1 - GSM8K | 19.03 | Accuracy (%) (5-shot) | 40.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 57.34 | Normalized accuracy (%) (25-shot) | 37.3 |
| Open LLM Leaderboard v1 - WinoGrande | 73.56 | Accuracy (%) (5-shot) | 32.6 |
| Open LLM Leaderboard v1 - MMLU | 53.17 | Accuracy (%) (5-shot) | 32.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.46 | MC2 (%) (0-shot) | 20.6 |
Interactive version: theaggregate.ai/model?slug=code-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.