tensor.news
Integrity IndexModelsCompareLabsPapersMethodologyAbout
tensor.news

© 2026

Evidence

  • Integrity Index
  • Model Claim Ledger
  • Compare

Entities

  • Models
  • Benchmarks
  • Labs
  • Papers

Method

  • Methodology
  • About
  • Privacy

Machine

  • Feed (Atom)
  • llms.txt
  • llms-full.txt
  • Sitemap

tensor.news grades benchmarks and tags model claims by evidence status. Every fact carries a source record and provenance. Scores are framed as task performance under a disclosed harness, never as deployed capability.

← Compare

phi-3-medium 14B vs phi-3-mini 3.8B

Verdict

phi-3-medium 14B leads 7–1 across 8 shared benchmarks.

phi-3-medium 14B 7 · phi-3-mini 3.8B 1 · higher isn't always better — see caveats.

Per-benchmark head-to-head

phi-3-medium 14Bphi-3-mini 3.8B
  • 33.7
    ANLI
    29.2
  • 88.8
    ARC AI2
    79.87
  • 75.2
    BBH
    62.27
  • 76.53
    HellaSwag
    68.93
  • 70.67
    MMLU
    58.4
  • 83.2
    OpenBookQA
    84
  • 73.9
    TriviaQA
    64
  • 63
    Winogrande
    41.6
A higher number is not always a better model. Each score is task performance under a disclosed harness, and some of these benchmarks are saturated or scored under mixed harnesses. Follow any benchmark to its integrity grade before reading a win as decisive.

Follow the record

These models

  • phi-3-medium 14B88.8
  • phi-3-mini 3.8B84