MANY MINDED · THE COST CURVES · KNOWLEDGE

How fast is the world’s fastest supercomputer?

Fastest supercomputer, computational capacity · GFLOP/s · measured 1993–2025 · fitted live from 33 observations by the Many Minded cost-curve engine.

The last measured value is 1.81B GF (2025, OWID / TOP500). Over the fitted window the series rises 48.9% a year (80% interval +22.4% to +81.0%) — a doubling every 1.7 years (80%: 1.2–3.4). Carried forward on that fit, 2030: 13.2B GF (80%: 2.43B GF–72.0B GF).

1.81B GFlatest measured (2025)+48.9%fitted, per year1.7yper doubling33observations, 1993–2025measuredbasis

the curve

fastest supercomputer — measured history and fitted projectionfastest supercomputer: measured 1993–2025 in GFLOP/s, last value 1.81B GF, fitted at 48.9% a year, projected to 2033 inside an 80% interval. Logarithmic vertical axis.GFLOP/s10010.0K1.00M100M10.0B1993199820032008201320182023202820331.81B GF (2025)
Vertical axis: GFLOP/s, log scale. Solid: measured observations. Dashed: the fitted central projection. Shaded: the 80% interval, which widens with horizon because shocks accumulate.

what this series measures

computational capacity of the world’s fastest supercomputer.

what the fit says

quantityvaluehow it is computed
fitted rate+48.9%/yr (80%: +22.4% to +81.0%)Farmer–Lafond drift over the trailing window · n=11 points, 10 years
doubling time1.7 years (80%: 1.2–3.4)implied by the fitted drift
curve checkdecelerating (83% → 54%/yr)first half of the record versus the second, judged against the direction that helps this metric (rising)
regime break~2011 (88% → 46%/yr, F=56.5)Chow-style best single breakpoint, kept only above a conservative sup-F threshold

Not shown for this curve, because the machinery returns nothing: Wright's law (no cumulative-deployment series for this technology).

the projection, with its interval

Log cost as a random walk with drift: the forecast variance grows with horizon (τ + τ²/m), which is why these bands widen instead of staying parallel. The middle column is the least useful number on this page; the interval is the claim.

yearcentral fit80% interval
20262.69B GF1.41B GF to 5.15B GFnear horizon
20274.01B GF1.54B GF to 10.5B GFnear horizon
20285.97B GF1.76B GF to 20.2B GFnear horizon
20298.88B GF2.05B GF to 38.4B GFthe band is already wide here
203013.2B GF2.43B GF to 72.0B GFthe band is already wide here
2031above 18.1B GFpast the point where a number would be theater

The table stops at 18.1B GF — a decade above the highest value ever observed here. Past that, quoting a number would be theater rather than forecast.

questions this page answers

How fast is the world’s fastest supercomputer?

1.81B GF as of 2025, the latest measured value in the series (OWID / TOP500). The fitted trend has it rising 48.9% a year, with an 80% interval of +22.4% to +81.0%.

How fast is the speed of the fastest supercomputer rising?

+48.9% a year over the fitted window, an 80% interval of +22.4% to +81.0% — a doubling every 1.7 years (80%: 1.2 to 3.4 years). Fitted from 11 observations spanning 10 years.

What will the speed of the fastest supercomputer be in 2030?

The central fit says 13.2B GF, inside an 80% interval of 2.43B GF to 72.0B GF. The interval is the forecast; the middle number is only its midpoint. Bands widen with horizon because shocks accumulate — a constant-width band would be overconfident.

Is the rise in the speed of the fastest supercomputer accelerating or slowing?

Splitting the record in half, the fitted rate went from 83% to 54% a year — decelerating. A Chow-style test finds a regime break around 2011 (88% → 46% a year, F=56.5). Regime breaks, not window choice, are what dominate this method's errors — which is why every projection here carries an interval.

Where does this data come from?

OWID / TOP500. 33 observations spanning 1993–2025. Curated benchmark history, extended by a weekly authoritative fetch and by news figures fact-checked against their source before they may touch a fit. Both the observation ledger and the fitting code are public, and the engine publishes its own calibration score and its misses.

the raw numbers

Every observation behind the fit, unrounded by us and unsmoothed. This table is here on purpose: graphs make people underestimate exponential change, and the raw series beside the curve is the one correction shown to work.

yearGFLOP/schange
1993124 GF
1994170 GF+37.1%
1995170 GF+0.0%
1996368 GF+116.6%
19971.34K GF+263.4%
19981.34K GF+0.0%
19992.38K GF+77.8%
20004.94K GF+107.6%
20017.23K GF+46.3%
200235.9K GF+396.3%
200335.9K GF+0.0%
200470.7K GF+97.2%
2005281K GF+296.8%
2006281K GF+0.0%
2007478K GF+70.4%
20081.10M GF+131.1%
20091.76M GF+59.2%
20102.57M GF+45.9%
201110.5M GF+309.6%
201217.6M GF+67.4%
201333.9M GF+92.5%
201433.9M GF+0.0%
201533.9M GF+0.0%
201693.0M GF+174.7%
201793.0M GF+0.0%
2018144M GF+54.3%
2019149M GF+3.6%
2020442M GF+197.4%
2021442M GF+0.0%
20221.10B GF+149.3%
20231.19B GF+8.3%
20241.74B GF+45.9%
20251.81B GF+3.8%

where this comes from

Other KNOWLEDGE curves:

Recent briefs from KNOWLEDGE, the daily record of what actually moved:

every KNOWLEDGE brief →

Every tracked curve: utility solar, installed · battery pack price · battery cell price · solar module price · human genome sequencing · onshore wind electricity · solar electricity (LCOE) · space launch, to LEO · wheat yield · offshore wind electricity · modular housing, turnkey · AI video, finished minute · humanoid robot, capable unit · cheapest humanoid, list price · farm labor share · healthcare spend per person

← the whole engine: build clock, cascade, calibration · the archive · how we know