# Prophetlab/Investor-Last-Exam > A buy-side benchmark for equity investment research featuring 86 assignments and a time-frozen corpus of 3.4 million document versions to test whether AI agents can form sound investment judgments using only information available at a historical cutoff. - Magnitude: 4.8 out of 10 — Early signal - Stars: 122 total · +0 stars measured 2026-10-31, 00:27–02:33 UTC, ≈ 88 by evening - Star trust: star growth looks organic - Category: Finance & crypto · Language: Python · Created: 2026-10-28 · Last push: 2026-10-31 - GitHub: https://github.com/Prophetlab/Investor-Last-Exam · Page: https://gitnova.dev/en/r/Prophetlab/Investor-Last-Exam ## Useful for - Evaluate how AI agents handle investment research under strict temporal restrictions - Compare LLM performance on forecasting accuracy, evidence reconciliation, and investment decision quality - Test whether agents can reconstruct financial statements and cash-flow identities from historical filings ## Why it’s here - Star-counter measurements on 2026-10-31 (UTC), 00:27–02:33: 122 → 122 stars (+0). This is the change over that interval. - Estimated end-of-day forecast: about +88 stars, using observed gains and the previous day. - The repository is 3 days old and already has 122 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #160. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 4 - Issues and pull requests: 2 - Watchers: 1 - Average over the last week: 52 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 0 ## Stars per day, last 4 days (oldest → newest, today is partial) 2026-10-28 … 2026-10-31: 6, 2, 112, 0 ## Spotted in now - Top new repositories this week: #160 ## More in this category 1. **tapoooooty/hypergrad** — 6.1 · Early signal · Finance & crypto · Python · +0 stars measured 2026-10-31, 00:35–02:33 UTC, ≈ 104 by evening A builder-deployed perp DEX on Hyperliquid for Solana memecoins graduating from pump.fun: a GRAD index perp plus individual perps for coins that hold their market cap. Full card: https://gitnova.dev/en/r/tapoooooty/hypergrad.md 2. **benderandrew069/deepseek-api-pricing-2026** — 4.5 · Early signal · Finance & crypto · +11 stars measured 2026-10-31, 00:28–02:33 UTC, ≈ 270 by evening · unusual star pattern (heuristic) A guide to estimating DeepSeek API costs in 2026, breaking down pricing by model, cache hits, and peak/off-peak hours with formulas and worked examples. Full card: https://gitnova.dev/en/r/benderandrew069/deepseek-api-pricing-2026.md 3. **Jakeschincariol/day-trader-skill** — 4.2 · Peaking · Finance & crypto · Python · +24 stars measured 2026-10-31, 00:27–02:33 UTC, ≈ 283 by evening A set of 11 Claude skills for day trading: chart scanning, news tracking, entry/exit timing, trade outcome simulation and risk checks on free public data. Full card: https://gitnova.dev/en/r/Jakeschincariol/day-trader-skill.md 4. **emmilco/us-tax-model** — 3.9 · Early signal · Finance & crypto · HTML · +1 star measured 2026-10-31, 00:27–02:33 UTC, ≈ 19 by evening Encodes US federal individual income tax forms and instructions as cited, machine-checkable YAML data, with a guided self-preparation interview that computes forms and explains every value locally. Full card: https://gitnova.dev/en/r/emmilco/us-tax-model.md 5. **QuantMLResearch/quant-handbook** — 3.9 · Early signal · Finance & crypto · Python · +4 stars measured 2026-10-31, 00:27–02:34 UTC, ≈ 29 by evening A quantitative investing handbook for A-shares: 8 modules and 31 lessons with Python scripts, covering PIT data, factors, ML, portfolio optimization and backtesting with T+1 and price limits. Full card: https://gitnova.dev/en/r/QuantMLResearch/quant-handbook.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-31 02:43 UTC, updated every 30 minutes.