Model Profile
Phi-3-small-128k-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-small-128k-instruct
Author: microsoft
Origin: huggingface_catalog
Arch: unknown
Benchmark Coverage
Scored use cases: 10
Avg confidence: 13.8%
Evidence points: 49
Raw rows: 82
Weighted rows: 5
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 772
Intelligence Profile
Dimension Breakdown
No eq benchmarks found
No creativity benchmarks found
No based benchmarks found
* Low confidence — limited benchmark evidence for this dimension
2/5 dimensions scored · Last updated Apr 2, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
RepoQA Official Results
overall_average_pass_at_1_pct
Normalized value 53.4% · confidence 100.0%
Strongest impact in Debugging assistant
repoqa_leaderboard.overall_average_pass_at_1_pct · Apr 1, 2026
BigCodeBench Official
bigcodebench_complete_pct
Normalized value 57.8% · confidence 100.0%
Strongest impact in IDE code completion
bigcodebench_official.bigcodebench_complete_pct · Apr 1, 2026
BigCodeBench Official
bigcodebench_instruct_pct
Normalized value 54.6% · confidence 100.0%
Strongest impact in IDE code completion
bigcodebench_official.bigcodebench_instruct_pct · Apr 1, 2026
RepoQA Official Results
all_average_pass_at_1_pct
Normalized value 53.4% · confidence 100.0%
Strongest impact in Unit test generation
repoqa_leaderboard.all_average_pass_at_1_pct · Apr 1, 2026
BigCodeBench Official
bigcodebench_hard_complete_pct
Normalized value 32.7% · confidence 100.0%
Strongest impact in IDE code completion
bigcodebench_official.bigcodebench_hard_complete_pct · Apr 1, 2026
Some fit rows have limited benchmark evidence.
10 of 10 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
10
Total Measurements
82
Weighted Measurements
5
Weighted Sources
2
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Debugging assistant use_case.dev.debugging | 9.5% |
| Unit test generation use_case.dev.test_generation | 8.8% |
| Code Review Assistant use_case.dev.code_review_assistant | 8.4% |
| Integration test generation use_case.dev.integration_tests | 7.9% |
| Refactoring assistant use_case.dev.refactoring | 7.4% |
| Verilog/VHDL generation use_case.eda.verilog_generation | 7.3% |
| Documentation from code use_case.dev.docstrings_and_docs | 6.3% |
| Code generation use_case.dev.code_generation | 5.4% |
| IDE code completion use_case.dev.ide_completion | 5.3% |
| Codebase onboarding brief use_case.dev.codebase_onboarding | 5.3% |