plutus-8B-instruct — benchmark results
TheFinAI's Plutus 8B instruct model, a Greek-finance fine-tune of Llama-Krikri-8B. Provider: Other. Released 2025-02-18. Access: Open.
Unified ELO 1884 ± 106, rank #74 of 1776 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FinBen - FinNum | 70.06 | Normalized Score | 100 |
| FinBen - MultiFin | 72.22 | Normalized Score | 100 |
| Open FinLLM Leaderboard | 55.9 | Average normalized score (self-reported) | 100 |
| FinBen - FinText | 57.15 | Normalized Score | 95.8 |
| FinBen - FNS | 34.46 | Normalized Score | 95 |
| FinBen - QA | 64 | Normalized Score | 84.2 |
| Greek MMLU - Greek-Specific | 73.96 | Accuracy (%) | 71.6 |
| Greek MMLU - Humanities | 69.74 | Accuracy (%) | 71.6 |
| Greek MMLU - Social Sciences | 69.73 | Accuracy (%) | 69.1 |
| Greek MMLU | 65.71 | Accuracy (%) | 67.9 |
| Greek MMLU - Other | 64.01 | Accuracy (%) | 67.9 |
| Greek MMLU - STEM | 61.65 | Accuracy (%) | 61.7 |
Interactive version: theaggregate.ai/model?slug=plutus-8b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.