clef-omni / .eval_results /safeagents-judge-bench.yaml
kp-cloudflare's picture ybelkada's picture
ybelkada HF Staff
Add safeagents judge bench v2 results (#7)
189097b
Raw History Blame
1.19 kB
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: balanced_accuracy
value: 0.877
date: "2026-11-10"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench/tree/v2
name: "safeagents judge bench v2, test split, run on NVIDIA A100 80GB (HF Jobs)"
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: auroc
value: 0.946
date: "2026-11-10"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench/tree/v2
name: "safeagents judge bench v2, test split, run on NVIDIA A100 80GB (HF Jobs)"
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: false_block_rate
value: 0.16
date: "2026-11-10"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench/tree/v2
name: "safeagents judge bench v2, test split, run on NVIDIA A100 80GB (HF Jobs)"
- dataset:
id: harness-hub/safeagents-judge-bench
task_id: category_macro_f1
value: 0.437
date: "2026-11-10"
source:
url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench/tree/v2
name: "safeagents judge bench v2, test split, run on NVIDIA A100 80GB (HF Jobs)"