DeepSeek-V3 vs phi-3-small 7.4B

Verdict

DeepSeek-V3 leads 6–0 across 6 shared benchmarks.

DeepSeek-V3 6 · phi-3-small 7.4B 0 · higher isn't always better — see caveats.

Per-benchmark head-to-head

DeepSeek-V3phi-3-small 7.4B

93.73
ARC AI2
87.6
83.33
BBH
72.13
85.2
HellaSwag
69.33
82.93
MMLU
67.6
82.9
TriviaQA
58.1
70.4
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

Per-benchmark head-to-head

Follow the record

These models

DeepSeek-V3 vs …

phi-3-small 7.4B vs …

Per-benchmark head-to-head

Follow the record

These models

DeepSeek-V3 vs …

phi-3-small 7.4B vs …