1,115 events · Updated 09:38 UTC

Where AI models agree and where they don't.

Track where frontier AI agrees, splits, and shifts across macro, rates, crypto, and policy. Every event is independently forecast and later verified against real outcomes.

GPT · Claude · Gemini · Grok
Where AI agrees right nowView all

EARNWill International Flavors & Fragrances Inc. (IFF) report Q1 FY2026 revenue above $2.6B?

45%

TRADEWill the US announce new Section 301 investigations by June 1, 2026?

66%

CRYPTOWill Solana exceed $95 by 2026-06-01?

68%

MACROWill US nonfarm payrolls for June 2026 exceed 200,000?

66%

MKTWill the S&P 500 close above 7,200 by July 12, 2026?

66%

ASIA Will China's Caixin manufacturing PMI exceed 50.0 in April 2026?

59%
0Active Forecasts
0%Avg Spread
0Resolved
0.248Brier (263)
Verified Accuracy263

events resolved and Brier scored

BRIER SCORE0.25Avg across 263 resolved
CRENE RESOLVED263Events verified & Brier scored
DATASET SCHEMA
question_id · category · consensus
spread · confidence · claude_prob
gpt4o_prob · gemini_prob · grok_prob
outcome · resolution_date · brier_score
Updated every 6 hours
1,115 active899 resolving 30d
HIGH
58%
MED
54%
LOW
58%

Accuracy by confidence tier · 263 resolved

Calibration curve
0%25%50%75%100%050100ACTUAL
Spread distribution
0-1010-2020-3030-4040-5050+
Average model probability
GPT55%Claude51%Gemini55%Grok56%
Data evaluated byNeudataEagle AlphaMonda
Download sample dataset
200 CRENE events · Full schema · 4 model probabilities
Methodology

Auditable pipeline, no black boxes

Every forecast follows the same structured process from event creation to verified outcome.

01
Detect
AI scans upcoming macro releases, policy decisions, and earnings dates. Questions structured with binary resolution criteria.
02
Forecast
GPT-4o-mini, Claude Haiku 4.5, Gemini 2.5 Flash Lite, and Grok 4 Fast independently predict each event. No model sees another's output.
03
Track
Every prediction timestamped with model reasoning, confidence, and belief trajectories as resolution approaches.
04
Verify
Outcomes verified against BLS, Fed, SEC filings. Every prediction gets a correct/incorrect label and Brier score.
Who this is for

Built for teams that need measurable signal

Quantitative Researchers
Structured AI belief data as an orthogonal signal. Model disagreement as a feature. Full history for backtesting and calibration analysis.
Macro Analysts
Multi-model consensus on every major economic event. Pre-computed views across CPI, NFP, FOMC, GDP, earnings, and central bank decisions.
Data Teams
Clean, schema-consistent API feed. Every field typed, every outcome resolved against authoritative sources where available, with full provenance stored per event.
APIREST + CSV EXPORT

Programmatic access to every forecast

Model reasoning, belief trajectories, resolution outcomes. Public endpoints for exploration. Authenticated for bulk export.

# Public endpoints
curl "https://api-get.crene.com/api/predictions/accuracy/"
curl "https://api-get.crene.com/api/predictions/edges/?min_edge=15"

# Prediction lifecycle
curl "https://api-get.crene.com/api/predictions/lifecycle/{question_id}/"

# Bulk export (authenticated)
curl -H "X-API-Key: crn_..." \
  "https://api-get.crene.com/api/export/predictions/?output=csv"

Legacy /api/predictions/ path retained for marketplace compatibility. Canonical /api/events/ aliases serve identical data.

Continue exploring

Events, divergence signals, and API documentation.