Phi-Line_14B: benchmark results
SicariusSicariiStuff's roleplay and creative-writing fine-tune of Microsoft's Phi-4 14B, tuned for low refusals and character-card adherence. Provider: Microsoft. Released 2025-02-17. Access: Open.
Unified ELO 1546 ± 1, rank #457 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 49.49 | Score | 98.3 |
| Open LLM Leaderboard - MATH Level 5 | 38.6 | Score | 89.1 |
| Open LLM Leaderboard - GPQA | 13.76 | Score | 88.9 |
| Open LLM Leaderboard - BBH | 43.79 | Score | 83.2 |
| Open LLM Leaderboard - MuSR | 14.78 | Score | 80.2 |
| Open LLM Leaderboard - IFEval | 64.96 | Score | 77.2 |
| UGI - Willingness (W/10) | 6.8 | W/10 Score | 67 |
| UGI Leaderboard | 30.47 | UGI Score | 32.7 |
| UGI - Natural Intelligence | 16.04 | NatInt Score | 24 |
Interactive version: theaggregate.ai/model?slug=phi-line-14b · How It Works · Data refreshed daily, snapshot 2026-09-05.