Claude
Anthropic
· 2026-08-28
Anthropic's Claude Sonnet. Tends toward balanced, well-calibrated analysis with moderate assumptions.
Calibration and accuracy describe observed behavior, not predictive ability. Experimental research — not investment advice. Terms of Use
▲Most Consistent1.1%/day
Claude is the most aggressive model — largest average valuation gap (+4.6%). Most stable day-to-day (1.10%/day). Wins: Most Consistent. High validity rate (98.4%).
Model Positioning
Calibration score vs estimate consistency
Key Metrics
+4.6%
Avg Gap
64/100
Calibration
13%
Correction Rate
47%
Positive Bias %
Consistent
Volatility
33
Days Tracked
Bias History
Model bias over time vs other models
Prediction Accuracy
Directional accuracy vs actual price changes
Directional Accuracy
52.2%
Mean Absolute Error
28.3%
Prediction Bias
+4.6%
Hit Rate (±5%)
19.5%
N = 763 · 1 Day
Current Estimates
Assumption Profile
7.4%
σ = 5.73
Revenue CAGR 5Y
9.3%
σ = 1.42
WACC
2.37%
σ = 0.45
Terminal Growth
23.9%
EBIT Margin Target
Validity
98.4%
2936 / 2984 validity rate
Cost & Performance
Avg Latency: 28.8s
Cost per Run: $0.0401
Total Cost: $119.51
~6776 + 1346 tokens
Calibration Detail
64
/100
Correction Rate: 13.2%
Uncapped Deviation: —
Total Valuations: 786
Want these insights weekly?
Subscribe to AI Signals →AI Investor Barometer · Claude← Back to dashboard
All content is generated by AI models and may contain errors. This is an experimental tool — not investment advice, research, or recommendation. Terms of Use · Privacy Policy