PiVoT-10.7B-Mistral-v0.2: benchmark results
Provider: maywell. Access: Open.
Aggregate Rating 1395 ± 28, rank #6321 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 30.03 | Normalized accuracy (%) | 81.8 |
| Open LLM Leaderboard v1 - WinoGrande | 80.03 | Accuracy (%) (5-shot) | 72 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 58.23 | MC2 (%) (0-shot) | 71.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 28.05 | Exact match, flexible extract (%) | 62.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.31 | Normalized accuracy (%) (25-shot) | 62.2 |
| Open Korean LLM Leaderboard | 36.86 | Average Score (%) | 59.3 |
| Open LLM Leaderboard v1 - GSM8K | 42.38 | Accuracy (%) (5-shot) | 57 |
| Open Korean LLM - Ko-EQ-Bench | 9.35 | EQ-Bench score | 55.4 |
| Open Korean LLM - KorNAT-Harmless | 63.08 | Normalized accuracy (%) | 55.1 |
| Open Korean LLM - KorNAT-Helpful | 47.25 | Normalized accuracy (%) | 54.7 |
| Open Korean LLM - Ko-IFEval | 28.43 | Strict accuracy, prompt/instruction mean (%) | 47.6 |
| Open LLM Leaderboard v1 - HellaSwag | 81.68 | Normalized accuracy (%) (10-shot) | 46.4 |
Interactive version: theaggregate.ai/model?slug=pivot-10-7b-mistral-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.