BTC 1-day forecast by GPT-5.6 Sol

GPT-5.6 Sol's 1-day forecast for BTC, made 2026-10-06: expected range $84,000.00 to $88,200.00 at 57% confidence. Settled at $82,947.83: direction called correctly, score 77.3.

AssetBTC
ModelGPT-5.6 Sol
Recorded byForecastnest
Forecast made
Horizon1-day (Continuous elapsed hours / calendar days; crypto trades 24/7.)
Window closes
Price when asked$86,444.71
Price the model reported$86,292.00
Expected range$84,000.00 to $88,200.00
Confidence57%
Prompt styleNo data
StatusSettled
Actual close$82,947.83
Traded range in the window$82,733.30 to $86,691.19
ResultDirection called correctly
Score77.3 of 100

The model's reasoning

(1) What I found, and where: CoinDesk's live markets page showed BTC at approximately $86,291.86 immediately after the 2026-10-06 14:54 UTC baseline, so I use $86,292 as the anchor. Earlier on October 6, BTC had been rejected near $87,000 for the third time since September 23, briefly traded near $85,200, and then recovered above $86,000. Sources: https://www.coindesk.com/markets and https://www.coindesk.com/markets/2026/10/06/bitcoin-keeps-getting-rejected-at-usd87-000-as-stocks-hover-near-records :chatgpt-content-reference{index=

Other models on the same question

ModelExpected rangeConfidenceResultScore
Perplexity$84,500.00 to $88,500.0055%Direction called incorrectly11.4
Gemini 1.5 Pro$84,800.00 to $88,500.0070%Direction called incorrectly10.7
Claude Sonnet 5.5$84,300.00 to $88,300.0055%No directional call49.2
Muse Spark 1.1$84,800.00 to $87,400.0058%Direction called correctly73.7
DeepSeek V3$84,600.00 to $87,600.0058%No directional call48.1
Grok 4.5$84,800.00 to $87,800.0048%Direction called incorrectly10.6

How this forecast is measured

Sends only the baseline price and the output format; your AI researches the asset itself. Best with a model that can search the web — it can reach news, filings and positioning we do not carry. Costs no market data, at generation or at settlement — you record the closing price yourself when the window shuts. The monthly allowance is what a membership buys, not a data bill.

Every model answering the same prompt is measured from the same starting price over the same window, and scored on its range and its call. How scoring works · All shared research.

ForecastNest provides AI-generated market analysis and quantitative research for informational and educational purposes only. Nothing here constitutes financial, investment, legal, or tax advice.