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

Llama 3-8B vs phi-3-small 7.4B

Verdict

phi-3-small 7.4B leads 5–1 across 6 shared benchmarks.

Llama 3-8B 1 · phi-3-small 7.4B 5 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Llama 3-8Bphi-3-small 7.4B
  • 35.95
    ANLI
    37.15
  • 77.07
    ARC AI2
    87.6
  • 58.4
    MMLU
    67.6
  • 76.8
    OpenBookQA
    84
  • 67.7
    TriviaQA
    58.1
  • 51.4
    Winogrande
    63
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

  • Llama 3-8B77.07
  • phi-3-small 7.4B87.6

phi-3-small 7.4B vs …

  • vs PowerMoE-3b
  • vs Claude Fable 5
  • vs GPT-5.5
  • vs Gemini 3.1 Pro
  • vs Llama 3.1-405B