Simreal AI

Pinned Loading

1. Simreal-MLBench Simreal-MLBench Public

   [Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

   Python 301 40

2. Xitadel-QuantBench Xitadel-QuantBench Public

   [Public preview] The first public quant trading benchmark scored against what professional traders actually made on the same asset

   Python 101 7

3. MathmoBench MathmoBench Public

   [Public preview] An advanced AI Benchmark for math, produced by mathmo at St John's College, Cambridge.

   Python 101 8

4. hard-puzzle-benchmark hard-puzzle-benchmark Public

   [Public preview] Hard human-written reasoning puzzles: 749 answered items in 15 topics (707 scored core), with protocol and scorer.

   Python 92 6

5. future-prediction-bench future-prediction-bench Public

   [Public alpha] Probability forecasting protocols, delayed-reward agent rollouts, and verifiable real-world task environments.

   Python 48 2