HLE Verified

Humanity’s Last Exam 的 verified subset。

HLE Verified 是 AgentCompass 中 Humanity’s Last Exam verified subset 的 benchmark entry。

​

Runtime Status

Field	Value
Benchmark id	hle_verified
Tags	Deep Research, Reasoning, Verified, Judge-Scored
Execution type	local with judge
Typical harness	researchharness 或 naive_search_agent
Typical environment	host_process
Current status	registered in the direct runtime

​

Run Example

agentcompass run \
  hle_verified \
  researchharness \
  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
category	过滤任务类别。
subset	过滤 verified subset metadata。
modality	llm 或 vlm。

​

Outputs

单任务详情写入 results/hle_verified/<model>/<run>/details/，聚合结果写入 summary.md。