Meltemi-7B-Instruct-v1.5: benchmark results
Provider: Other.
Aggregate Rating 1492 ± 39, rank #2482 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FinBen - FinText | 50.13 | Normalized Score | 87.5 |
| Open FinLLM Leaderboard | 28.35 | Average normalized score (imported) | 66.7 |
| Greek MMLU - Humanities | 63.99 | Accuracy (%) | 63 |
| Greek MMLU - Other | 61.03 | Accuracy (%) | 58 |
| Greek MMLU - Greek-Specific | 66.42 | Accuracy (%) | 56.8 |
| Greek MMLU - Social Sciences | 64.31 | Accuracy (%) | 55.6 |
| Greek MMLU | 60.93 | Accuracy (%) | 54.3 |
| Greek MMLU - STEM | 57.18 | Accuracy (%) | 53.1 |
Interactive version: theaggregate.ai/model?slug=meltemi-7b-instruct-v1-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.