ghost-7B-v0.9.0: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1341 ± 25, rank #7945 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 11.43 | EQ-Bench score | 57.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 21.61 | Exact match, flexible extract (%) | 53.9 |
| Open Korean LLM - Ko-IFEval | 28.95 | Strict accuracy, prompt/instruction mean (%) | 50 |
| Open LLM Leaderboard v1 - GSM8K | 33.74 | Accuracy (%) (5-shot) | 49.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.79 | MC2 (%) (0-shot) | 38.7 |
| Open LLM Leaderboard v1 - MMLU | 55.09 | Accuracy (%) (5-shot) | 35.4 |
| Open LLM Leaderboard v1 - WinoGrande | 73.72 | Accuracy (%) (5-shot) | 33.3 |
| Open LLM Leaderboard v1 - HellaSwag | 77.93 | Normalized accuracy (%) (10-shot) | 32.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.07 | Normalized accuracy (%) (25-shot) | 28.5 |
| Open Korean LLM - KorNAT-CKA | 19.32 | Normalized accuracy (%) | 23.8 |
| Open Korean LLM Leaderboard | 29.89 | Average Score (%) | 15 |
Interactive version: theaggregate.ai/model?slug=ghost-7b-v0-9-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.