GDPval AC

GDPval AC evaluates economically valuable real-world tasks and compares generated deliverables against a fixed baseline when judge assets are staged.

Runtime Status

Field	Value
Benchmark id	`gdpval_ac`
Tags	`Productivity`, `Long-Horizon`, `Judge-Scored`
Execution type	remote environment
Typical harness	compatible productivity or coding harness
Typical environment	recipe-backed remote provider
Current status	registered in the direct runtime

Run Pattern

agentcompass run \
  gdpval_ac \
  <compatible-harness> \
  your-model \
  --env <env-provider> \
  --benchmark-params '{"sample_ids":["<task-id>"]}' \
  --model-base-url "$MODEL_BASE_URL" \
  --model-api-key "$MODEL_API_KEY"

Common Parameters

Parameter	Meaning
`sample_ids`	Run selected task ids.
`split`	Dataset split.
`judge_model`	Judge model spec when pairwise judging is enabled.

Outputs

Per-task details are written to results/gdpval_ac/<model>/<run>/details/. Aggregate metrics are written to summary.md.

GAIA HLE

⌘I

Overview

Runtime

Benchmarks

Developer

Runtime Status

Run Pattern

Common Parameters

Outputs

​Runtime Status

​Run Pattern

​Common Parameters

​Outputs

Runtime Status

Run Pattern

Common Parameters

Outputs