AI Model Observatory
Five AIs, five personalities. Compare how they value the same stocks daily.
Model Scorecard
All five models compared on bias, calibration, accuracy, cost and validity. Click any row to read the full profile.
| Model | Bias | Calib. | Accuracy | Cost / run | Latency | Validity | |
|---|---|---|---|---|---|---|---|
| GPT | -1.9% | 59/100 | 52%n=964 | $0.0165 | 10.5s | 97.5% | Read profile → |
| Claude | +0.7% | 60/100 | 50%n=960 | $0.0384 | 28.7s | 97.0% | Read profile → |
| Gemini | -0.7% | 55/100 | 47%n=948 | $0.0103 | 17.8s | 95.9% | Read profile → |
| DeepSeek | -4.4% | 57/100 | 48%n=989 | $0.0022 | 19.9s | 100.0% | Read profile → |
| Grok | -2.0% | 55/100 | 49%n=981 | $0.0154 | 7.3s | 99.2% | Read profile → |
Model Personalities
Each model has a distinct fingerprint — these are the patterns we see in production.
GPT
The perpetual bear
Most pessimistic of the five. Notably defaults its terminal-growth assumption to 2.0% almost every time, which biases DCF outputs downward.
Most negative bias-1.9%
Read full profile →
Claude
The cautious calibrator
Least bearish of the five and the best calibrated. Tends to anchor close to analyst consensus and rarely needs engine corrections.
Best calibration60/100
Read full profile →
Gemini
The variance king
Highest spread in growth assumptions and the most likely to trip the engine's PE cap. Bold calls, rougher calibration.
Highest CAGR variance55/100
Read full profile →
DeepSeek
The disciplined one
Cheapest model in the lineup and the most consistent at producing valid outputs. Moderate bias, low drama.
Lowest cost$0.0022/run
Read full profile →
Grok
The speed demon
Fastest end-to-end and the most likely to hit engine caps. Confident estimates that the calibration layer pulls back hard.
Fastest latency7.3s
Read full profile →
Bias History
How each model's average valuation gap has shifted day by day. Closer to the zero line = closer to market price.
Most Positive: GPT (-3.2% avg 44d)Most Negative: DeepSeek (-9.6% avg 44d)
GPT
Claude
Gemini
DeepSeek
Grok
Where Models Disagree Most This Week
Stocks where the five AI models can't agree. Big spread = the universe's hardest names to value right now.
02
METAMeta Platforms Inc.σ 15.2%
highestGPT+79.0%lowestDeepSeek+17.4%
03
GOOGLAlphabet Inc.σ 10.8%
highestGPT+28.3%lowestDeepSeek-3.7%
Go deeper