Claude Sonnet 4 vs Gemini 2.5 Flash (Sep 2025)

Verdict

Gemini 2.5 Flash (Sep 2025) leads 2–1 across 3 shared benchmarks.

Claude Sonnet 4 1 · Gemini 2.5 Flash (Sep 2025) 2 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Claude Sonnet 4Gemini 2.5 Flash (Sep 2025)

33.1
The Agent Company
41.1
1
VPCT
19.3
46.11
WeirdML
41.91

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

Claude Sonnet 484.37
Gemini 2.5 Flash (Sep 2025)41.91