Code-Mistral-7B [bfloat16] [rev: ed3b9ad58391]: benchmark results
A Mistral fine-tune by ajibawa-2023 using QLoRA and coding, Orca math and OpenHermes datasets, with ChatML prompts. Training method, stored weight dtype and evaluated runtime quantization are separate properties. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1434 ± 34, rank #4489 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 68.08 | Accuracy (%) (5-shot) | 85.1 |
| Open LLM Leaderboard v1 - WinoGrande | 82.24 | Accuracy (%) (5-shot) | 83 |
| Open LLM Leaderboard v1 - MMLU | 65 | Accuracy (%) (5-shot) | 80 |
| Open LLM Leaderboard v1 - HellaSwag | 85.29 | Normalized accuracy (%) (10-shot) | 73.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.59 | Normalized accuracy (%) (25-shot) | 67.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 54.64 | MC2 (%) (0-shot) | 63.1 |
Interactive version: theaggregate.ai/model?slug=code-mistral-7b-bfloat16-rev-ed3b9ad58391 · How It Works · Data refreshed daily, snapshot 2026-11-08.