← Back to Models·

GPT

OpenAI
· 2026-07-31
OpenAI's GPT-4.1 model. Known for systematic analysis with conservative terminal growth assumptions.
Calibration and accuracy describe observed behavior, not predictive ability. Experimental research — not investment advice. Terms of Use
GPT is a moderate model with an average valuation gap of -3.3%. Most volatile day-to-day (4.60%/day). High validity rate (98.1%).

Model Positioning

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

Key Metrics

-3.3%
Avg Gap
65/100
Calibration
17%
Correction Rate
38%
Positive Bias %
High Variance
Volatility
14
Days Tracked

Bias History

Model bias over time vs other models

Prediction Accuracy

Directional accuracy vs actual price changes
Directional Accuracy
51.3%
Mean Absolute Error
32%
Prediction Bias
-3%
Hit Rate (±5%)
9.6%
v8.10%25%50%75%100%14.7.16.7.20.7.22.7.24.7.28.7.30.7.DeepSeekClaudeGeminiGrokGPT
N = 312 · 1 Day

Current Estimates

Largest Positive Gap
+104.2%
+36.6%
+36.0%
+24.2%
+18.1%
Largest Negative Gap
-57.0%
-48.4%
-41.6%
-40.6%
-39.4%

Assumption Profile

6.7%
σ = 6.49
Revenue CAGR 5Y
9.4%
σ = 1.27
WACC
2.01%
σ = 0.07
Terminal Growth
24.5%
EBIT Margin Target

Validity

98.1%
2479 / 2528 validity rate

Cost & Performance

Avg Latency: 9.4s
Cost per Run: $0.0174
Total Cost: $43.88
~5330 + 404 tokens

Calibration Detail

65
/100
Correction Rate: 16.7%
Uncapped Deviation:
Total Valuations: 336
Want these insights weekly?
Subscribe to AI Signals →
AI Investor Barometer · GPT← 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