CodeMaster-v1-7B: benchmark results
Provider: Other.
Aggregate Rating 1207 ± 38, rank #9581 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 37.94 | Accuracy (%) (5-shot) | 19.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 39.59 | Normalized accuracy (%) (25-shot) | 15.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.65 | MC2 (%) (0-shot) | 14.8 |
| Open LLM Leaderboard v1 - HellaSwag | 55.46 | Normalized accuracy (%) (10-shot) | 12.3 |
| Open LLM Leaderboard v1 - WinoGrande | 57.62 | Accuracy (%) (5-shot) | 10.8 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=codemaster-v1-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.