← Back to Models·

Claude

Anthropic
· 2026-05-01
Anthropic's Claude Sonnet. Tends toward balanced, well-calibrated analysis with moderate assumptions.
Highest Calibration60 score
Most Consistent1.0%/day
Lowest Correction Rate43% bullish
~Market Pulse+0.7%
Claude is the most aggressive model — largest average valuation gap (+0.7%). Most stable day-to-day (1.00%/day). Wins: Highest Calibration, Most Consistent, Lowest Correction Rate, Market Pulse. High validity rate (97.0%).

Model Positioning

Calibration score vs estimate consistency
Calibrated & ConsistentConsistent but UncalibratedCalibrated but VolatileLow ScoresCalibrationConsistencyGPTCLAUDEGEMINIDEEPSEEKGROK
Compare:GPTGeminiDeepSeekGrok

Key Metrics

+0.7%
Avg Gap
60/100
Calibration
35%
Correction Rate
43%
Positive Bias %
Consistent
Volatility
44
Days Tracked

Bias History

Model bias over time vs other models

Prediction Accuracy

Directional accuracy vs actual price changes
Directional Accuracy
49.6%
Mean Absolute Error
18.9%
Prediction Bias
+0.5%
Hit Rate (±5%)
19.5%
0%25%50%75%100%3.3.11.3.19.3.27.3.6.4.14.4.22.4.30.4.
GPT51.5%
Claude49.6%
Gemini47.3%
DeepSeek48.1%
Grok49.3%
N = 960 · 1 Day

Current Estimates

Largest Positive Gap
+45.7%
+38.0%
+35.8%
+30.0%
+20.6%
Largest Negative Gap
-34.9%
-22.9%
-18.7%
-18.1%
-17.7%

Assumption Profile

7.4%
σ = 5.89
Revenue CAGR 5Y
9.3%
σ = 1.24
WACC
2.37%
σ = 0.45
Terminal Growth
24.2%
EBIT Margin Target

Validity

97.0%
982 / 1012 validity rate

Cost & Performance

Avg Latency: 28.7s
Cost per Run: $0.0384
Total Cost: $38.89
~6431 + 1346 tokens

Calibration Detail

60
/100
Correction Rate: 34.9%
Uncapped Deviation:
Total Valuations: 982
AI Investor Barometer · Claude← Back to Models
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