ineqmath/ineqmath
Mathematics
Reasoning
IneqMath: Olympiad-level inequality benchmark with expert-reviewed test problems, formulated as bound-estimation and relation-prediction subtasks with stepwise judging.
Run this task
CLI:
inspect eval inspect_harbor/ineqmath --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import ineqmath
eval(ineqmath(), model="openai/gpt-5")Dataset information
| Harbor registry | ineqmath/ineqmath |
| Inspect task | ineqmath |
| Latest digest | sha256:c3fd4f273b6e88713188b8b4d01d1701dbd7b39c41e0bdcc3e8d097aeadcc9b7 |
| Samples | 100 |
| Paper | arxiv |
| Source | https://github.com/lupantech/ineqmath |
See Task Parameters for the parameter set shared across all Harbor tasks.