LLM Evaluatology Leaderboard
Dataset
Evaluation methods
Original: original questions + default configuration;
SCS: original questions + sampling over the full configuration space;
A-SCS: augmented questions + sampling over the full configuration space.
SCS: original questions + sampling over the full configuration space;
A-SCS: augmented questions + sampling over the full configuration space.
Vendors
Leaderboard (sort: click ▲/▼ on column header)
Dataset: AIME · Method: Original · Models: 0 · Showing: 0-0
| Rank | Model | ACC |
|---|---|---|
| No data | ||