CarbonVillain-10.7B-v1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1462 ± 17, rank #1432 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.11 | Accuracy (%) | 82.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 40.41 | Exact match, flexible extract (%) | 75 |
| Open Korean LLM - KorNAT-CKA | 28.06 | Normalized accuracy (%) | 73.4 |
| Open Korean LLM - Ko-EQ-Bench | 26.15 | EQ-Bench score | 72.8 |
| Open Korean LLM Leaderboard | 38.3 | Average Score (%) | 66 |
| Open Ko-LLM Leaderboard | 38.3 | Average (%) | 65.9 |
| Open Korean LLM - KorNAT-Helpful | 48.1 | Normalized accuracy (%) | 64.6 |
| Open Korean LLM - KorNAT-Harmless | 63.1 | Normalized accuracy (%) | 55.8 |
| Open Korean LLM - Ko-IFEval | 30.07 | Strict accuracy, prompt/instruction mean (%) | 54.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=carbonvillain-10-7b-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.