HomeInsidersWhalesCohortsAllocationsLiquidityThe TableNewsEmissionsBuybacksX-RaySmart MoneyOutflowsData APIPricing
● Live insider tape…
Subnets / SN18

Zeus SN18

Zeus (subnet 18) is a Bittensor subnet held by 2,007 unique coldkeys. Its liquidity pool holds 9.6k τ, with the alpha token trading at 0.0035 τ. Roughly 1% of tracked holders are in profit — most bought in above today's price. Seller exhaustion is elevated: 86% of recent sellers have emptied their wallets, thinning the supply overhang. Full insider flow, whale tracking and the complete proprietary factor set for Zeus are available to SubnetStats subscribers.
SCREENER
ALPHA PRICE
0.0035 τ
IN TAO
HOLDERS
2,007
UNIQUE COLDKEYS
POOL DEPTH
9.6k τ
TAO IN POOL
7D MOMENTUM
-3.3%
ALPHA vs TAO
01

30-day alpha price

as of 2026-11-08
Project activity
@zeussubnet
2d ago
✍️ @taodaily_io on Zeus
3d ago
Imagine a weather system that doesn't settle for one model's strenghts and weaknesses. One that continuously identifies the best-performing models for each variable and intelligently routes every API request to the right specialist. That's Zeus Pro. Temperature 👉 UID 224 Wind
5d ago
📸 Current Zeus leaderboard snapshot! Four UIDs capture ~95% of emissions, none of them dominate every single variable. 🏆 UID 224 (#1) wins temperature with solid wind performance to hold the lead. UID 85 (#2) absolutely dominates solar, but capped by its 20% scoring weight. U
10d ago
Since June 17th, we've hashed every single Zeus forecast to the blockchain. Now, 25K times our historical forecast archive has been downloaded on HuggingFace. Our trustless verification mechanism allows anyone to check that a published forecast matches the hash commited on-chai
17d ago
With teams dedicating thousands of hours to model development on Zeus, stable evaluation is the most important aspect of the subnet’s design. AI brings a new generation of weather models that rival (and outperform) traditional numerical models. Ground truths, loss functions and
19d ago
How long until Zeus miners launch their own satellites? 🛰️
20d ago
Is Zeus Pro getting better over time? Yes! From June to September, Zeus Pro showed statistically significant improvements in relative forecasting skill against four operational baselines. Competitive pressure on Bittensor: a mechanism for real innovation. 🔗 https://t.co/IyxLa1
25d ago
Zeus' full @ExploitSummit talk @RoryZeus breaks down the how and why of Zeus, shares what’s ahead, and pitches Zeus Pro and Zeus Edge 👇 https://t.co/JkKO4cKvLb
27d ago
US natural gas traders are betting on a mild winter, with net-short positions exceeding 140K contracts. ❄️ But unexpected cold snaps will turn the market upside down. This winter, it's about the next 10 days of weather. Zeus temperature forecasts as population-weighted HDD/CDD
2026-10-08 ago
For a 00Z model run, Zeus disseminates in around 1.5 hours. That’s a 4.5 hour time advantage for energy traders to position before others trading with industry-standard models. This is our strongest differentiator. https://t.co/YiXciAohOq
2026-10-07 ago
Bittensor 101, featuring Zeus @mcjkula & @TAOTemplar break it down at @ExploitSummit A great intro to Bittensor, and to what can be built on it 👇
2026-09-24 ago
An hour and a half. That's how fast Zeus delivers a new weather run. That's 4× faster than IFS (6h) and nearly 5× faster than Google's new WeatherNext 3 (7h). And it's not winning on speed alone. 👇 We’ve put WeatherNext 3 head-to-head with our Zeus Pro and the industry-standar
2026-09-18 ago
NEW! Full-on benchmarking environment to see how Zeus performs, where and when. Zeus vs ECMWF’s IFS & AIFS singles and ensembles, across regions, lead times and variables. 🔗 https://t.co/sVGW0euRn9 https://t.co/y7nhCyfp8O
2026-09-18 ago
Built a full-on benchmarking dashboard to see where it excels, where it breaks, and how to make it even better. Zeus Pro vs ECMWF’s IFS & AIFS singles and ensembles, across regions, lead times and variables. Accessible to all. Now on the website. 🔗 https://t.co/sVGW0euRn9
2026-09-09 ago
Zeus is energy-aware. How? 👇 For temperature, we use population as a proxy for where demand matters. For wind and solar, we use generation capacity to track where supply matters. Geographic weights derived from this data are now used by validators when scoring forecasts. They’r
2026-09-03 ago
While energy supply becomes more and more weather-dependent, our mission is to give traders the fastest, most precise view on weather ✅ 75% faster* ✅ >30% more accurate on temperature* ✅ >20% more accurate on wind* *vs ECMWF IFS across June and July
2026-08-31 ago
Zeus (SN18), recent sell pressure resolved. An early partner who covered the slot registration fee (and held a share of emissions in return) decided to wind down and move on. Although we do not agree with the decision, we respect it. Their remaining position has been fully boug
2026-08-28 ago
Zeus gets a 10/10 from Arbos, by @const_reborn https://t.co/ZqKWZYW05l
2026-08-25 ago
Zeus is becoming energy-aware. The first among weather models. Incentives are now skewed towards Europe, most to Germany. Based on expressed interest from trading desks and trading volume. Within, they're further distributed, variable-specific, based on where weather drives ene
2026-08-21 ago
Tuesday... Deploying a new geographic incentive system that weights grid points based on variable-specific factors influencing energy supply and demand takes a bit more time than we thought. The intention, weight maps & methodology behind it will follow the mainnet update.
2026-08-18 ago
Make weather forecasting innovation even more responsive to what energy traders value. Based on our own research and input from traders across 12 desks. Deploying it to mainnet on Friday.
2026-08-10 ago
Energy trading is a >$3 trillion market. Every trading desk prices off the same weather model. It runs 4 times a day, and lands at the same time, every time. The second it lands, the market violently re-prices. We deciced to FRONT-RUN it. https://t.co/seIrf8FjgR
2026-08-05 ago
A forecast comes alive on the map, from temperature changes to shifting wind patterns. Here's 24 hours of weather across Australia & New Zealand. Powered by Zeus API. 🗺️ https://t.co/Q4jezTMNuE https://t.co/CuuujxBIte
2026-08-03 ago
1 Week into the beta waitlist for Zeus Edge. 50+ sign ups. Meetings had with 10 trading desks. More this week. The demand is there. Now... it's time to accelerate its development.
2026-07-31 ago
During this phase of pilots, we'll boost geographic scalars on Zeus. A 2.5x scalar (= error multiplier) on Germany drove a ~40% performance lead over IFS. What happens at 10x, 20x, 30x? 🚀
Posts by the project. Not a signal.
02

Proprietary signals

a sample — full set on the screener
SELLERS DRAINED
86%
28D SELLERS EMPTIED OUT
CAPITULATION
+0.18
BOUNCE COMPOSITE (z)
HEAT 7D
0.23×
VOLUME ÷ POOL DEPTH
HOLDERS IN PROFIT
1%
TRACKED WALLETS · ENTRY BELOW PRICE
WHAT'S CARRYING THE PRICE · 30DMIXEDemission rank #56 · below the bar (rank 32)
30D RETURN
-8.4%
ALPHA vs TAO
WITHOUT CHAIN BUYS
-8.4%
SAME 30 DAYS, PROTOCOL BID REMOVED
CHAIN SHARE OF BUYING
—
CHAIN BUYS vs TRADERS' NET
CHAIN BUYS / DAY
0 τ
PROTOCOL BUYING ITS ALPHA
Since the Emissions Gate, about two-thirds of emission is the protocol buying alpha on the pool. PROPPED = the chain carried the price while traders sold; ORGANIC = traders were net buyers and it beat the median without the chain. A description, not a forecast. How it works →
See who's buying and selling Zeus — every trade classified miner / validator / owner / outsider, plus holder cost basis and the full 23-factor screener.
OPEN THE INSIDER TAPE →
← SN17All subnetsSN19 →
Figures computed from Bittensor chain records. Not investment advice.
Bittensor subnet intelligence · Powered by TAOstats API · Methodology v1.0 · Not investment advice© SubnetStats · @SubnetStats · Feedback