Microsoft
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Running this yourself: desktop gpu should be enough.
55.2
Quality Score
1221
Arena ELO
14B
Parameters
16K
Context
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
0
Downloads
0
Likes
Jan 2025
Released
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
unsloth/phi-4 — Open LLM Leaderboard #217
Avg: 40.7 | IFEval: 68.8 | BBH: 55.3 | MATH: 50.0 | GPQA: 11.5 | MMLU-PRO: 48.6
View sourcePhi-4 Benchmark Update
Quality: 10.4/100 | Price: $0.219/M tokens | Output: 36.239 tok/s | MMLU: 0.714% | HumanEval: 0.231%
View sourcephi-4 — LiveBench Scores
language: 0.2 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.4
View sourceunsloth/phi-4 — Open LLM Leaderboard #217
Avg: 40.7 | IFEval: 68.8 | BBH: 55.3 | MATH: 50.0 | GPQA: 11.5 | MMLU-PRO: 48.6
View sourcePhi-4 Benchmark Update
Quality: 10.4/100 | Price: $0.219/M tokens | Output: 38.043 tok/s | MMLU: 0.714% | HumanEval: 0.231%
View sourcephi-4 — LiveBench Scores
language: 0.2 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.4
View source1221
ELO Score
1218 - 1225
95% Confidence
+/-4 points
25.2K
Battles
May 20, 2026
Last Updated