gaia@1.0
Assistants
Multimodal
GAIA (General AI Assistants): 165 validation tasks for multi-step reasoning, tool use, and multimodal question answering.
Run this task
CLI:
inspect eval inspect_harbor/gaia_1_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import gaia_1_0
eval(gaia_1_0(), model="openai/gpt-5")Dataset information
| Harbor registry | gaia@1.0 |
| Inspect task | gaia_1_0 |
| Version | 1.0 |
| Samples | 165 |
| Paper | arxiv |
See Task Parameters for the parameter set shared across all Harbor tasks.