← Back to Models·

DeepSeek

DeepSeek
· 2026-06-17
DeepSeek's chat model. Outstanding reliability at the lowest cost, with moderate bearish tendency.
$Lowest Cost$0.0022/run
Highest Validity100.0%
DeepSeek is the most conservative model — smallest average valuation gap (-5.4%). Moderate daily volatility (1.70%/day). Wins: Lowest Cost, Highest Validity. Perfect validity rate (100%). Cheapest model at $0.0022/run.

Model Positioning

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

Key Metrics

-5.4%
Avg Gap
67/100
Calibration
20%
Correction Rate
34%
Positive Bias %
Responsive
Volatility
77
Days Tracked

Bias History

Model bias over time vs other models

Prediction Accuracy

Directional accuracy vs actual price changes
Directional Accuracy
47.6%
Mean Absolute Error
17.9%
Prediction Bias
-5.5%
Hit Rate (±5%)
12.8%
v6v7v80%25%50%75%100%3.3.20.3.8.4.27.4.14.5.2.6.16.6.DeepSeekClaudeGeminiGrokGPT
N = 1748 · 1 Day

Current Estimates

Largest Positive Gap
+64.7%
+32.1%
+12.1%
+10.8%
+8.8%
Largest Negative Gap
-45.9%
-39.7%
-39.4%
-26.3%
-25.4%

Assumption Profile

6.6%
σ = 5.82
Revenue CAGR 5Y
9.6%
σ = 1.23
WACC
2.04%
σ = 0.15
Terminal Growth
23.7%
EBIT Margin Target

Validity

100.0%
1771 / 1771 validity rate

Cost & Performance

Avg Latency: 13.8s
Cost per Run: $0.0022
Total Cost: $3.90
~5582 + 629 tokens

Calibration Detail

67
/100
Correction Rate: 19.6%
Uncapped Deviation:
Total Valuations: 138
Want these insights weekly?
Subscribe to AI Signals →
AI Investor Barometer · DeepSeek← 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