MacroLens - Public Company Valuation: leaderboard
Zero-shot valuation of U.S. small- and micro-cap companies (MacroLens, Trirat et al., 2026): from point-in-time fundamentals, macroeconomic state, filing text and derived valuation ratios, the model estimates market capitalization for a 1,324-ticker company-level holdout. Median absolute percentage error in percent, with per-instance errors capped at 1,000%, for LLMs run with reasoning disabled; lower is better.
Metric: Median absolute percentage error (%; market-capitalization estimate for the 1,324-ticker company-level holdout from fundamentals, macroeconomic state, filings and derived valuation ratios; per-instance APE capped at 1,000%; daily granularity; zero-shot LLM with reasoning disabled). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 (Non-reasoning) | 73.22 | #225 (GPT-5.1) |
| 2 | Qwen 3.5 27B (Non-reasoning) | 89.16 | #358 (Qwen 3.5 27B) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=macrolens-public-company-valuation · How It Works · Data refreshed daily, snapshot 2026-11-12.