← Back to dashboard·

DeepSeek

DeepSeek
· 2026-05-22
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 (-4.9%). Moderate daily volatility (1.90%/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

-4.9%
Avg Gap
56/100
Calibration
45%
Correction Rate
33%
Positive Bias %
Responsive
Volatility
59
Days Tracked

Bias History

Model bias over time vs other models

Prediction Accuracy

Directional accuracy vs actual price changes
Directional Accuracy
47.1%
Mean Absolute Error
18.2%
Prediction Bias
-5%
Hit Rate (±5%)
11.7%
v6v70%25%50%75%100%3.3.17.3.31.3.14.4.28.4.12.5.21.5.DeepSeekClaudeGeminiGrokGPT
N = 1334 · 1 Day

Current Estimates

Largest Positive Gap
+30.0%
+26.7%
+21.3%
+13.2%
+12.2%
Largest Negative Gap
-45.0%
-25.6%
-23.6%
-23.4%
-21.2%

Assumption Profile

6.5%
σ = 5.84
Revenue CAGR 5Y
9.6%
σ = 1.26
WACC
2.05%
σ = 0.17
Terminal Growth
23.6%
EBIT Margin Target

Validity

100.0%
1357 / 1357 validity rate

Cost & Performance

Avg Latency: 16.5s
Cost per Run: $0.0022
Total Cost: $2.99
~5539 + 641 tokens

Calibration Detail

56
/100
Correction Rate: 45.4%
Uncapped Deviation:
Total Valuations: 1357
Want these insights weekly?
Subscribe to AI Signals →
AI Investor Barometer · DeepSeek← 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