argus

BTC/USD Volatility 15m

block 11,987,527 · settled 2026-11-20 21:41 UTC

The network said
σ 0.00389
32 models, 6 forecasters
What happened
σ 0.00806
our reconstruction
Network miss
0.417 pp
combined against truth
Spread
σ 0.00100
widest to narrowest model
Every model that answeredranked by distance from what happened
#ModelSaidOff byvs network
1allo1ea9z2mf35…a8z6σ 0.004410.365 ppbeat it
2allo1h4grarj6r…lcv8σ 0.004400.367 ppbeat it
3allo15zn66ex9c…wzs9σ 0.004160.391 ppbeat it
4allo1kety7w05v…0e8tσ 0.004140.392 ppbeat it
5allo12yzys7fsj…hwtcσ 0.004090.398 ppbeat it
6allo1m50xsnscq…wn3mσ 0.004080.399 ppbeat it
7allo122pcawdm8…csmwσ 0.004050.401 ppbeat it
8allo1as93w68f7…2muyσ 0.004040.402 ppbeat it
9allo1hf0ut5ads…86a8σ 0.004000.406 ppbeat it
10allo16q3exe6jx…j6gmσ 0.003970.410 ppbeat it
11allo1ljzpfy45r…z5xzσ 0.003930.414 ppbeat it
12allo1cgah085g9…nundσ 0.003930.414 ppbeat it
13allo1xqtjs4sld…sg7xσ 0.003910.416 ppbeat it
14allo109ucl7nz7…wthlσ 0.003900.417 ppbeat it
15allo1nau5puf0e…c7seσ 0.003880.418 ppbehind
16allo1ceu8sq8cp…mgqcσ 0.003870.419 ppbehind
17allo13egv8dpmg…m4w5σ 0.003840.422 ppbehind
18allo1q92d4m6n0…4zmtσ 0.003780.429 ppbehind
19allo17dr9cvrv9…0jukσ 0.003770.429 ppbehind
20allo1p0kw6slnr…zzt2σ 0.003770.430 ppbehind
21allo10vy4x2hgu…ng3gσ 0.003760.431 ppbehind
22allo1cx2q70d0t…vj02σ 0.003740.432 ppbehind
23allo1n7f5v7g8q…7pf3σ 0.003730.433 ppbehind
24allo1a8pck9eje…jpfyσ 0.003730.433 ppbehind
25allo1r6japwzy0…tx5fσ 0.003720.434 ppbehind
26allo1q8ym49trt…xkmdσ 0.003710.435 ppbehind
27allo1kuhy5lhga…uqp4σ 0.003710.436 ppbehind
28allo1j86peucw2…kex7σ 0.003630.443 ppbehind
29allo1qjg0hg09z…34mnσ 0.003620.445 ppbehind
30allo120uv2d4zp…c49lσ 0.003450.462 ppbehind
31allo1tccwj0kyt…g3h0σ 0.003440.462 ppbehind
32allo127u03lmhs…4nkrσ 0.003420.465 ppbehind

"Beat it" means this model landed closer to what happened than the network's combined answer did. actual is our independent reconstruction from spot candles: exact for log returns and prices, estimator-dependent for volatility.

Forecasters · 6

A forecaster does not predict the asset. It predicts which models are about to be wrong, and its call is what moves the network's answer off the plain mean of σ 0.00386.