d3-ultra / .eval_results /safeagents-judge-bench.yaml
Xunzhuo's picture adaamko's picture
Add safeagents judge bench results (#3)
ccdcfa6
Raw History Blame Contribute Delete
1.19 kB
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: balanced_accuracy
value: 0.756
date: "2026-10-30"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
name: "safeagents judge bench v0, test split, run on 2 x NVIDIA A40 (sharded, CUDA bf16)"
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: auroc
value: 0.994
date: "2026-10-30"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
name: "safeagents judge bench v0, test split, run on 2 x NVIDIA A40 (sharded, CUDA bf16)"
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: false_block_rate
value: 0.487
date: "2026-10-30"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
name: "safeagents judge bench v0, test split, run on 2 x NVIDIA A40 (sharded, CUDA bf16)"
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: category_macro_f1
value: 0.491
date: "2026-10-30"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
name: "safeagents judge bench v0, test split, run on 2 x NVIDIA A40 (sharded, CUDA bf16)"