Verdict
phi-3-small 7.4B leads 6–1 across 8 shared benchmarks.
phi-3-mini 3.8B 1 · phi-3-small 7.4B 6 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: phi-3-small 7.4B leads 2–0 across 3 shared reasoning benchmarks (largest gap: BBH, 72.13 vs 62.27 — single evaluator).
Commonsense Reasoning: phi-3-small 7.4B leads 2–0 across 2 shared commonsense reasoning benchmarks (largest gap: Winogrande, 63 vs 41.6 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
No vendor claims on file for phi-3-mini 3.8B.
General
“Phi-3-Small-8K-Instruct is a 7B parameters, lightweight, state-of-the-art open model”
Reasoning
“Phi-3-Small-8K-Instruct showcased a robust and state-of-the-art performance among models of the same-size and next-size-up”
phi-3-small 7.4B leads 6–1 across 8 shared benchmarks. phi-3-mini 3.8B leads 1 benchmark and phi-3-small 7.4B leads 6, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
phi-3-mini 3.8B and phi-3-small 7.4B have 8 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
phi-3-small 7.4B leads reasoning 2–0. phi-3-small 7.4B leads commonsense reasoning 2–0.