Bucharest-0.3: benchmark results
Provider: Other.
Aggregate Rating 1427 ± 33, rank #4789 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 82.72 | Accuracy (%) (5-shot) | 85.2 |
| Open LLM Leaderboard v1 - MMLU | 65.61 | Accuracy (%) (5-shot) | 84.9 |
| Open LLM Leaderboard v1 - HellaSwag | 84.46 | Normalized accuracy (%) (10-shot) | 66.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.99 | Normalized accuracy (%) (25-shot) | 65.1 |
| Open LLM Leaderboard v1 - GSM8K | 51.18 | Accuracy (%) (5-shot) | 63.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.19 | MC2 (%) (0-shot) | 33.7 |
Interactive version: theaggregate.ai/model?slug=bucharest-0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.