Add signalbench (In-Band Signal Compliance) community eval
YAML Metadata Error:Invalid content in Eval Result file .eval_results/signalbench.yaml
Check out the documentation for more information.
Show details
YAML Metadata Error:Invalid content in Eval Result file .eval_results/signalbench.yaml
Check out the documentation for more information.
Show details
YAML Metadata Error:Invalid content in Eval Result file .eval_results/signalbench.yaml
Check out the documentation for more information.
Show details
YAML Metadata Error:Invalid content in Eval Result file .eval_results/signalbench.yaml
Check out the documentation for more information.
Show details
YAML Metadata Error:Invalid content in Eval Result file .eval_results/signalbench.yaml
Check out the documentation for more information.
Show details
YAML Metadata Error:Invalid content in Eval Result file .eval_results/signalbench.yaml
Check out the documentation for more information.
Show details
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# signalbench community eval for mistralai/Mistral-Nemo-Instruct-2407
|
| 2 |
+
# Submit as a PR: add this file to mistralai/Mistral-Nemo-Instruct-2407/.eval_results/signalbench.yaml
|
| 3 |
+
# Source system id (OpenRouter): openrouter:mistralai/mistral-nemo | seed 0 | n=75
|
| 4 |
+
|
| 5 |
+
- dataset:
|
| 6 |
+
id: thamilvendhan/signalbench
|
| 7 |
+
task_id: src
|
| 8 |
+
value: 0.3167
|
| 9 |
+
date: "2026-07-08"
|
| 10 |
+
source:
|
| 11 |
+
url: https://huggingface.co/datasets/thamilvendhan/signalbench
|
| 12 |
+
name: signalbench raw per-item responses
|
| 13 |
+
user: thamilvendhan
|
| 14 |
+
notes: "SRC overall; deterministic action-based grader, no LLM judge; seed 0, n=75"
|
| 15 |
+
- dataset:
|
| 16 |
+
id: thamilvendhan/signalbench
|
| 17 |
+
task_id: time
|
| 18 |
+
value: 0.5833
|
| 19 |
+
date: "2026-07-08"
|
| 20 |
+
source:
|
| 21 |
+
url: https://huggingface.co/datasets/thamilvendhan/signalbench
|
| 22 |
+
user: thamilvendhan
|
| 23 |
+
notes: "family=time; n=12"
|
| 24 |
+
- dataset:
|
| 25 |
+
id: thamilvendhan/signalbench
|
| 26 |
+
task_id: access_deny
|
| 27 |
+
value: 0.0833
|
| 28 |
+
date: "2026-07-08"
|
| 29 |
+
source:
|
| 30 |
+
url: https://huggingface.co/datasets/thamilvendhan/signalbench
|
| 31 |
+
user: thamilvendhan
|
| 32 |
+
notes: "family=access_deny; n=12"
|
| 33 |
+
- dataset:
|
| 34 |
+
id: thamilvendhan/signalbench
|
| 35 |
+
task_id: memory_label
|
| 36 |
+
value: 0.3333
|
| 37 |
+
date: "2026-07-08"
|
| 38 |
+
source:
|
| 39 |
+
url: https://huggingface.co/datasets/thamilvendhan/signalbench
|
| 40 |
+
user: thamilvendhan
|
| 41 |
+
notes: "family=memory_label; n=12"
|
| 42 |
+
- dataset:
|
| 43 |
+
id: thamilvendhan/signalbench
|
| 44 |
+
task_id: injection
|
| 45 |
+
value: 0.5
|
| 46 |
+
date: "2026-07-08"
|
| 47 |
+
source:
|
| 48 |
+
url: https://huggingface.co/datasets/thamilvendhan/signalbench
|
| 49 |
+
user: thamilvendhan
|
| 50 |
+
notes: "family=injection; n=12"
|
| 51 |
+
- dataset:
|
| 52 |
+
id: thamilvendhan/signalbench
|
| 53 |
+
task_id: bot_policy
|
| 54 |
+
value: 0.0833
|
| 55 |
+
date: "2026-07-08"
|
| 56 |
+
source:
|
| 57 |
+
url: https://huggingface.co/datasets/thamilvendhan/signalbench
|
| 58 |
+
user: thamilvendhan
|
| 59 |
+
notes: "family=bot_policy; n=12"
|