Phi 4 Mini Instruct
Phi 4 Mini Instruct has too few ranked results yet to rate it on any capability.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability.
No capability has enough ranked results to rate yet.
Price
No current price is tracked for this model. See the rate card
Evidence
39results on35benchmarks
- 4 independently verified
- 17 aggregator
- 15 vendor-reported
- 3 cross-referenced
From 4 sources · latest Oct 8, 2026 · How verification works
API features
Structured outputs
As listed by OpenRouter
Phi 4 Mini Instruct benchmark results
39 results on 35 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond33.13Oct 8, 2026gpqa
- Humanity's Last Exam4.45Oct 8, 2026aa_hle
Show 2 more reasoning resultsHide 2 reasoning results
- GPQA Diamond25.20Oct 7, 2026GPQA
- 4.20May 15, 2026
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard0.00Oct 8, 2026aa_terminalbench_hard
- SciCode10.76Sep 4, 2026aa_scicode
- Terminal-Bench 2.10.37Aug 12, 2026terminalbenchV21
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- τ-Bench V3 · Banking1.03Aug 10, 2026tauBanking
0 of 3 ranked benchmarks measured
- 15.33Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench21.09Oct 8, 2026aa_ifbench
- 21.00May 15, 2026
0 of 4 ranked benchmarks measured
- Vectara HHEM hallucination ratelower is better23.50Jun 19, 2026
- AA-Omniscience · Accuracy9.50Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination22.01Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 420.20Jun 19, 2026
- 92.50Jun 19, 2026
- 76.50Jun 19, 2026
- AA Intelligence6.33Oct 8, 2026aa_intelligence_index
- -61.08Oct 8, 2026
- τ²-Bench Telecom (AA run)8.19Oct 8, 2026aa_tau2
Show 17 more resultsHide 17 results
- 0.34Aug 10, 2026
- ARC-Challenge83.70Oct 7, 2026ARC-C
- 32.80Sep 8, 2026
- Artificial Analysis Coding Index3.84Sep 9, 2026aa_coding_index
- BBH70.40Oct 7, 2026BIG-Bench Hard
- 81.20Oct 7, 2026
- 88.60Oct 7, 2026
- 69.10Oct 7, 2026
- 63.90Oct 7, 2026
- 52.80Oct 7, 2026
- 47.00May 15, 2026
- 49.30Oct 7, 2026
- 79.20Oct 7, 2026
- 77.60Oct 7, 2026
- 72.50Oct 7, 2026
- 66.40Oct 7, 2026
- 67.00Oct 7, 2026
Phi 4 Mini Instruct: common questions
Who makes Phi 4 Mini Instruct?
Phi 4 Mini Instruct is made by Microsoft.
When was Phi 4 Mini Instruct released?
Phi 4 Mini Instruct was released on Feb 26, 2024, according to Artificial Analysis.
How many benchmarks has Phi 4 Mini Instruct been tested on?
We track 39 results for Phi 4 Mini Instruct on 35 benchmarks from 4 sources, 4 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Phi 4 Mini Instruct support?
OpenRouter lists structured outputs for Phi 4 Mini Instruct.
About this record
Where Phi 4 Mini Instruct's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- Jun 11, 2026
Where the results come from
Verification: 39 scores · 4 independently verified · 17 aggregator-attributed · 3 vendor cross-reference · 15 vendor-reported. How these tiers are assigned
From 4 sources on 4 sites. Artificial Analysis supplies 17 of them; the 4 independently verified results come from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai17
- api.llm-stats.com15
- raw.githubusercontent.com4
- huggingface.co3