Chart · millijoules a run

filter into a new table, in energy.

neo 21.6 mJ in the energy run. Closest: Polars at 1.02×. Farthest: Spark at 65.0×.

—

neo crosses once

neo

TAKE THIS CHART WITH YOU

Embed anywhere.

<iframe src="https://n0.is/embed/chart/filter-table-energy" title="filter into a new table, in energy" width="100%" height="520" loading="lazy" sandbox="allow-scripts" referrerpolicy="no-referrer" style="border:0;border-radius:12px"></iframe>

Every engine's multiple of neo

  1. neo
    1×
  2. Polars
    1.02× · 22.0 vs 21.6
  3. pandas
    4.04× · 87.0 vs 21.6
  4. DuckDB
    26.3× · 568 vs 21.6
  5. Spark
    65.0× · 1,402 vs 21.6

Bars to scale, from zero to the slowest engine. The gray pair is the engine's measurement and neo's in the same run, in mJ.

What this measures

Keep the rows whose amount is over 500 and build a new table of them, about half the file, every column copied. Energy is the same run in millijoules: what the machine billed each engine's whole process tree, with its draw at rest subtracted for the seconds of the window. neo's pool is told to rest after the kernel, as the editor tells it.

What neo is held to

The same rows every other engine keeps, every column copied, checked by the same line.

Each side, this kernel only

Polars1.02× neo · neo vs Polars

Polars, this kernel · neon-cpp/bench/lang/python/yardstick.py:218
timed("filter_mat", lambda: df.filter(pred))

pandas4.04× neo · neo vs pandas

pandas, this kernel · neon-cpp/bench/lang/python/yardstick.py:197
timed("filter_mat", lambda: df[amount > 500])

DuckDB26.3× neo · neo vs DuckDB

DuckDB, this kernel · neon-cpp/bench/lang/python/yardstick.py:237
timed("filter_mat", lambda: con.execute("CREATE OR REPLACE TABLE f AS SELECT * FROM t WHERE amount > 500"))

Spark65.0× neo · neo vs Spark

Spark, this kernel · neon-cpp/bench/lang/python/yardstick.py:255
timed("filter_mat", lambda: sink(df.filter(pred)))

neo · confidential

neo's kernels, the ports written in-house to beat them, and the techniques behind both stay with the engine. Nothing about how the numbers were made is withheld: the method, the checks every engine had to pass, every number and every place neo is behind are on this page. The engine itself we keep confidential, because we don't want it getting into the wrong hands. The binaries run on request and reproduce every number here.

Measured on Apple M5 Max, 18 cores, 26.4.1, 2026-10-11. Every number here is also on the comparison page of its engine, with how it was taken and the caveats.

All evalsEvery comparisonStart a conversation