SeaPhi3: benchmark results
Provider: Other.
Aggregate Rating 1492 ± 37, rank #2479 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Italian LLM - MMLU-Pro (IT) | 39.13 | Accuracy (%) | 100 |
| Pinocchio Italian - Cultura | 68.83 | Accuracy (%) | 90.9 |
| Pinocchio Italian - Diritto | 59.55 | Accuracy (%) | 90.9 |
| Pinocchio Italian - Generale | 65.12 | Accuracy (%) | 90.9 |
| Pinocchio Italian - Logica | 50.07 | Accuracy (%) | 90.9 |
| Pinocchio Italian - Matematica E Scienze | 61.28 | Accuracy (%) | 90.9 |
| Pinocchio Italian Leaderboard | 63.08 | Average Accuracy (%) | 90.9 |
| Pinocchio Italian - Lingua Straniera | 73.63 | Accuracy (%) | 88.6 |
Interactive version: theaggregate.ai/model?slug=seaphi3 · How It Works · Data refreshed daily, snapshot 2026-11-08.