deepseek-v4-flash vs gemini-3.6-flash

Capability for the money

gemini-3.6-flash costs 17.1× more than deepseek-v4-flash without measurably beating it on hard reasoning (GPQA Diamond), the only test both have sat — on that evidence the extra spend buys nothing you can point at.

1. Hard reasoning

   graduate-level science and multi-step analysis

   GPQA Diamond
   deepseek-v4-flash90.8%

   gemini-3.6-flash92.8%

   gemini-3.6-flash +2.0

Averaged over the benchmarks both models sat, deepseek-v4-flash returns 518.9 points of pass rate per dollar of blended price against 30.9 — the ratio that decides whether the dearer model earns its rate.

Each figure is a pass rate: the share of that test set the model answered correctly, measured by a third party rather than self-reported by the lab. Rows are different tests of different difficulty, so compare a model against the other model, not one row against the next. No published following instructions, coding or tool use score for one of these models, so those lenses are omitted. And a benchmark is not your workload — it narrows the shortlist, it does not pick for you.