Model Profile
Phi-3.5-mini-instruct
Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.
Identity
ID: microsoft/Phi-3.5-mini-instruct
Author: microsoft
Origin: huggingface_catalog
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 24.0%
Evidence points: 70
Raw rows: 22
Weighted rows: 8
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 293,196
Intelligence Profile
Dimension Breakdown
* Low confidence — limited benchmark evidence for this dimension
5/5 dimensions scored · Last updated May 1, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
Open LLM Leaderboard MMLU-Pro
mmlu_pro_accuracy_pct
Normalized value 47.0% · confidence 100.0%
Strongest impact in Social post generation
openllm_mmlu_pro_official.mmlu_pro_accuracy_pct · May 1, 2026
Open LLM Leaderboard GPQA
gpqa
Normalized value 40.7% · confidence 100.0%
Strongest impact in Social post generation
openllm_gpqa_official.gpqa · May 1, 2026
Open LLM Leaderboard IFEval
ifeval
Normalized value 64.2% · confidence 100.0%
Strongest impact in Job description drafting
openllm_ifeval_official.ifeval · May 1, 2026
EQ-Bench Leaderboard
eq_bench_score
Normalized value 61.0% · confidence 100.0%
Strongest impact in Social post generation
eq_bench.eq_bench_score · May 1, 2026
Open LLM Leaderboard BBH
bbh
Normalized value 47.7% · confidence 100.0%
Strongest impact in Brand voice localization
openllm_bbh_official.bbh · May 1, 2026
JSONSchemaBench Leaderboard
medium_schema_compliance_pct
Normalized value 53.0% · confidence 100.0%
Strongest impact in Claims summary
jsonschemabench_leaderboard.medium_schema_compliance_pct · May 1, 2026
Some fit rows have limited benchmark evidence.
7 of 12 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
122
Total Measurements
22
Weighted Measurements
8
Weighted Sources
7
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Social post generation use_case.mkt.social_post_generation | 12.9% |
| Product positioning and messaging use_case.mkt.product_positioning | 12.9% |
| Campaign brief use_case.mkt.campaign_brief | 12.9% |
| Personalized sales outreach use_case.mkt.sales_outreach_personalized | 12.4% |
| Ad copy variants use_case.mkt.ad_copy_variants | 12.4% |
| Job description drafting use_case.hr.job_description_drafting | 11.1% |
| Brand voice localization use_case.mkt.brand_voice_localization | 11.0% |
| Candidate summary memo use_case.hr.candidate_summary | 10.5% |
| Tail spend categorization use_case.proc.tail_spend_categorization | 10.3% |
| Claims summary use_case.ins.claims_summary | 10.0% |
| Kubernetes manifest generation use_case.sre.iac_k8s | 9.8% |
| Screenplay scene writing use_case.creative.screenplay_scene | 9.8% |