WizardVicuna-open-llama-3B-v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1252 ± 10, rank #2800 of 2928 rated models, from 78 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Physics | 32.45 | Accuracy (%) | 65.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| MMLU-by-task - College Physics | 25.49 | Accuracy (%) | 53.1 |
| MMLU-by-task - High School Statistics | 39.35 | Accuracy (%) | 53.1 |
| MMLU-by-task - Global Facts | 33 | Accuracy (%) | 51.5 |
| Open Korean LLM - Ko-IFEval | 26.94 | Strict accuracy, prompt/instruction mean (%) | 41.1 |
| MMLU-by-task - Security Studies | 40.41 | Accuracy (%) | 40.7 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 39 |
| MMLU-by-task - Professional Accounting | 29.43 | Accuracy (%) | 37.5 |
| MMLU-by-task - Formal Logic | 26.98 | Accuracy (%) | 35.6 |
| MMLU-by-task - Business Ethics | 35 | Accuracy (%) | 34.2 |
| MMLU-by-task - Electrical Engineering | 31.03 | Accuracy (%) | 34.2 |
Interactive version: theaggregate.ai/model?slug=wizardvicuna-open-llama-3b-v2 · How It Works · Data refreshed daily, snapshot 2026-09-23.