Historical scope reviewed September 8, 2026. The decay estimates belong to the original score generation and selected cohort. Target overlap and survival reduce the independent evidence; a strategy may change inside the same model slot. No atomic-era out-of-sample decay estimate is established here. See the current metric definitions.
Half of all staked model-rounds in the Classic tournament now burn NMR. The average staked model's MMC is the most negative it has ever been. Net payout per round has fallen from 179 bps of stake in 2020 to 8.7 bps in 2026, a 95% compression. And yet the tournament has never been busier: roughly 13,000 models were scored per Classic round in July 2026, up from 8,000 a year earlier, and 874,365 NMR sits at stake across the three tournaments.
That contrast is the subject of this deep dive. "Is the alpha decaying?" is really three questions. Is the crowd predicting worse (skill)? Is the average model contributing less on top of the crowd (edge)? And does a unit of performance pay less than it used to (yield)? Using about 4.2 million staked model-round records from 2020 through mid-2026 (Classic only, and only rounds old enough for their 60-day metrics to have fully settled), the comparisons describe changing scores and per-round payouts; they do not identify a causal decay in strategy quality.
The tournament itself is fine
First the denominator. As of July 12, 2026 there are 874,365 NMR at stake (about $8.4M at $9.64 per NMR) across 6,635 staked models: 5,133 Classic, 877 Signals, 625 Crypto. Total stake is up 5.3% since the April statistical snapshot, and scored models per Classic round jumped 62% year over year, driven largely by the no-stake submission surge. Participation and collateral are growing. Whatever is decaying, it is not interest in the tournament.
Test 1: raw skill is cyclical, not decaying
CORJ60 measures what a model is ultimately for: correlation between its predictions and realized 60-day targets. If the crowd were losing its ability to forecast the market, the field's median CORJ60 should trend down. It doesn't — it cycles.
The yearly averages of the per-round median tell the story: 0.030 in 2021, down to 0.012 in 2023, back to 0.029 in 2024 (essentially a rerun of the 2021 peak), then 0.005 in 2025, the worst year on record. The 26-round rolling mean dipped below zero around the turn of 2026, its first sub-zero stretch ever, before recovering; fully-settled 2026 rounds average 0.009 and the spring readings were strong. This is regime, the same force the market regimes post documents. Verdict on skill decay: not proven. 2025 was brutal, but 2024 was one of the best years in tournament history.
Test 2: historical mean contribution declined
MMC measures contribution after accounting for the meta-model; originality alone does not guarantee a positive score (primer here). And by that yardstick the average participant is losing ground in a way that is not cyclical.
The field-wide median MMC (every scored model, benchmarks excluded) has been negative before, but never like this: −0.0022 in 2025 and −0.0034 in 2026, nearly seven times deeper than any earlier year. Among staked models specifically, the rolling equal-weight mean bottomed near −0.0029 in early 2026. The stake-weighted mean, by contrast, has held slightly above zero since mid-2025, the widest sustained gap between the two lines in tournament history. The same split shows up in raw accuracy: stake-weighted CORJ60 in 2026 is 0.020 versus 0.011 equal-weight. The weighted and equal-weight score summaries differ in this selected sample. They do not establish that allocation caused the difference.
Composition remains a possible explanation. Stakes settled per round have drifted down, from about 5,200 in 2024 to 4,100 in 2026, but that count alone cannot rule out changes in the scored population. It fits instead with two forces this blog has tracked separately: cross-model dispersion compressing roughly 40% since 2019 (metric convergence) and within-model aging, where even long-lived survivors decay as the meta-model absorbs their signal.
The consequences land in wallets. In 2020–2022, 26–29% of staked model-rounds burned. The share spiked briefly to 60% in the brutal mid-2023 stretch, averaged 46% across 2025, and sits at 50% in 2026 after peaking near 59% early in the year. Meanwhile the share of staked models posting positive MMC fell from 52% in 2021 to 42% now. Loss frequency and score-sign frequency are separate statistics; neither alone determines expected payout.
Test 3: the price of alpha, compressed 95%
Even where edge survives, it converts to far less NMR than it used to.
Net payout per round (earned minus burned, as a share of everything at stake) has fallen from 179 bps in 2020 to 8.7 bps in 2026. Most of that is mechanical: the payout factor slid from 1.00 to about 0.10 as the staked pool grew from an average of 115K NMR at risk per round to 693K. Cadence, target and payout multipliers also changed, so the factor alone does not imply a tenfold reduction in investor return: December 2025 and April 2026 both printed negative net payouts for the whole field.
How to interpret this historical sample
The archived figures describe selected pre-atomic score distributions and net NMR per round. Daily and weekly payout cadence, score definitions, population changes and overlapping targets limit comparisons across years. The per-round basis-point bars are not annual yields, account returns or an estimate of the price of an unchanged unit of skill.
Classic moved to atomic staking at round 1343. Its payout factor is 1 under the observed configuration, with different score multipliers and separately funded positions. The historical low-factor narrative therefore does not describe today's payout rule. Use current metrics and the settled-outcome view for the applicable definitions.