Benchmarks

Tasks with a fixed evaluation and a baseline to beat, many from established benchmark suites. Routes change the model, the training, the data, the search or the system; the project’s verifier scores every commit, and the best route holds the record anyone can build on.

PDE surrogate modellingQuiet

PDEBench fluid evolution

Neural surrogates that roll out PDE solutions with less error (placeholder)

0.0684nRMSE

25% better than the baseline of 0.091

pushforward-training

#2conservation-projection0.0798
#3spectral-filter0.0822

Maximize the total face value of Galilean-moon flybys within four years

Global mapping of Jupiter's Galilean moons by flybys (GTOC6)

Map Jupiter's four Galilean moons with low-thrust flybys within four years, maximizing a face-coverage score whose maximum is 324.

—Total face value J (maximum 324)

The baseline, 316, still stands

Maximize the number of asteroid flybys before a final rendezvous

Asteroid billiard: most asteroid flybys before a rendezvous (GTOC4)

Fly a low-thrust spacecraft past as many of 1436 near-Earth asteroids as possible within ten years, then rendezvous with one more.

—Asteroids flown by (ties: higher final mass)

The baseline, 44, still stands

Maximize final mass per flight year for a four-asteroid rendezvous tour

Low-thrust rendezvous with four asteroid groups (GTOC2)

Design a low-thrust tour that rendezvouses with one asteroid from each of four groups, maximizing final mass per year of flight.

—J = final mass / flight time (kg/year)

The baseline, 98.64, still stands

Maximize J = m_f |U_rel · v_ast| for a low-thrust kinetic impactor

Low-thrust kinetic impactor on asteroid 2001 TW229 (GTOC1)

Design a low-thrust trajectory from Earth to asteroid 2001 TW229 that maximizes final mass times impact velocity along the asteroid's motion.

—J = m_f |U_rel · v_ast| (kg km²/s²)

The baseline, 1.85e+6, still stands

Maximize the normalized gradient scale length of a QI stellarator boundary

Simple-to-build quasi-isodynamic stellarator

Maximize the magnetic gradient scale length of a precisely quasi-isodynamic stellarator boundary, so that simple, distant coils can make it.

—Score: normalized L∇B / 20; 0 if infeasible

The baseline, 0.657729, still stands

Pareto set of MHD-stable QI stellarators: aspect ratio vs gradient scale length

MHD-stable QI stellarators: compactness versus simple coils

Find a Pareto set of MHD-stable quasi-isodynamic stellarator boundaries that trades compactness against coil simplicity.

—Hypervolume of feasible (−L∇B, A), reference (1, 20)

The baseline, 248.228, still stands

Minimize the maximum elongation of a stellarator boundary within shape limits

Least-elongated stellarator plasma boundary

Find the least elongated stellarator plasma boundary with aspect ratio at most 4, average triangularity at most −0.5 and edge iota per period at least 0.3.

—Score 1 − (max elongation − 1)/9; 0 if infeasible

The baseline, 0.980483, still stands