Codesota · Models · Phi-4-mini-instructmicrosoft14 results · 3 benchmarks
Model card

Phi-4-mini-instruct.

microsoftopen-source3.84B params
§ 01 · Benchmarks

Every benchmark Phi-4-mini-instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score50.5%#54/101—source ↗
02CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions1.3%#78/93—source ↗
03CPTU-BenchNatural Language Processing · Polish Text Understandingaverage2.2%#82/93—source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding2.4%#82/93—source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench45.3%#84/299—source ↗
06CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment2.7%#86/93—source ↗
07CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology2.2%#87/93—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in78.4%#121/490—source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage43.3%#173/491—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele75.2%#176/490—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk50.8%#188/489—source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc64.4%#292/490—source ↗
13Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd19.0%#348/490—source ↗
14Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book71.6%#406/489—source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where Phi-4-mini-instruct actually performs.

Natural Language Processing
3
benchmarks
avg rank #161.2
§ 04 · Related models

Other microsoft models scored on Codesota.

Phi-3-medium-4k-instruct
0 results
Phi-3-mini-4k-instruct
0 results
Phi-3-small-8k-instruct
0 results
Phi-3.5-MoE-instruct
0 results
Phi-3.5-mini-instruct
3.82B params · 0 results
phi-4
14.7B params · 0 results
🚧WizardLM-2-7B
0 results
§ 05 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
8
results
SpeakLeash/CPTU-Bench
5
results
SpeakLeash/Polish-EQ-Bench
1
result
14 of 14 rows marked verified.