| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_benign |
sonnet-5-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
7.1 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall |
2.9 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
7.1 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall) |
2.9 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud |
7.1 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall |
2.9 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
7.1 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_adversarial |
sonnet-5-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall) |
2.9 |
| strong_reject |
sonnet-5-openrouter |
default |
strong_reject_scorer |
jailbreak_rate |
0.0 |
| strong_reject |
sonnet-5-openrouter |
default |
strong_reject_scorer |
strong_reject_metric |
0.0 |
| coconot |
sonnet-5-openrouter |
default |
model_graded_qa |
Requests with safety concerns |
0.0 |
| coconot |
sonnet-5-openrouter |
default |
model_graded_qa |
total |
0.0 |
| xstest_unsafe |
sonnet-5-openrouter |
default |
model_graded_qa |
refusal_rate |
80.0 |
| xstest_safe |
sonnet-5-openrouter |
default |
model_graded_qa |
refusal_rate |
0.0 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge |
hle/accuracy |
0.6 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge |
hle/cerr |
0.4 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge1 |
hle/accuracy |
0.6 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge1 |
hle/cerr |
0.4 |
| hle |
gemini-3.8-flash-openrouter |
tight |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge |
hle/accuracy |
0.6 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge |
hle/cerr |
0.4 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge1 |
hle/accuracy |
0.6 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge1 |
hle/cerr |
0.4 |
| hle |
gemini-3.8-flash |
tight |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
sonnet-5 |
tight |
hle/regex_judge |
hle/accuracy |
0.4 |
| hle |
sonnet-5 |
tight |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
sonnet-5 |
tight |
hle/regex_judge |
hle/cerr |
0.5 |
| hle |
sonnet-5 |
tight |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
sonnet-5 |
tight |
hle/regex_judge1 |
hle/accuracy |
0.4 |
| hle |
sonnet-5 |
tight |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
sonnet-5 |
tight |
hle/regex_judge1 |
hle/cerr |
0.5 |
| hle |
sonnet-5 |
tight |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge |
hle/accuracy |
0.2 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge |
hle/cerr |
0.8 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge1 |
hle/accuracy |
0.2 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge1 |
hle/cerr |
0.8 |
| hle |
gpt-5.4-mini |
tight |
hle/regex_judge1 |
hle/unscored |
0.0 |
| bfcl_simple_python |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_simple_python |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_simple_python |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
simple_python_acc |
1.0 |
| bfcl_simple_python |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_simple_python |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
simple_python_sterr |
0.0 |
| bfcl_simple_python |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_simple_python |
gemini-3.8-flash |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_simple_python |
gemini-3.8-flash |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_simple_python |
gemini-3.8-flash |
default |
bfcl_scorer |
simple_python_acc |
1.0 |
| bfcl_simple_python |
gemini-3.8-flash |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_simple_python |
gemini-3.8-flash |
default |
bfcl_scorer |
simple_python_sterr |
0.0 |
| bfcl_simple_python |
gemini-3.8-flash |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_simple_python |
sonnet-5 |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_simple_python |
sonnet-5 |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_simple_python |
sonnet-5 |
default |
bfcl_scorer |
simple_python_acc |
1.0 |
| bfcl_simple_python |
sonnet-5 |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_simple_python |
sonnet-5 |
default |
bfcl_scorer |
simple_python_sterr |
0.0 |
| bfcl_simple_python |
sonnet-5 |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_simple_python |
gpt-4.1 |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_simple_python |
gpt-4.1 |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_simple_python |
gpt-4.1 |
default |
bfcl_scorer |
simple_python_acc |
1.0 |
| bfcl_simple_python |
gpt-4.1 |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_simple_python |
gpt-4.1 |
default |
bfcl_scorer |
simple_python_sterr |
0.0 |
| bfcl_simple_python |
gpt-4.1 |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_simple_python |
gpt-5.4-mini |
default |
bfcl_scorer |
accuracy |
0.8 |
| bfcl_simple_python |
gpt-5.4-mini |
default |
bfcl_scorer |
stderr |
0.2 |
| bfcl_simple_python |
gpt-5.4-mini |
default |
bfcl_scorer |
simple_python_acc |
0.8 |
| bfcl_simple_python |
gpt-5.4-mini |
default |
bfcl_scorer |
all |
0.8 |
| bfcl_simple_python |
gpt-5.4-mini |
default |
bfcl_scorer |
simple_python_sterr |
0.2 |
| bfcl_simple_python |
gpt-5.4-mini |
default |
bfcl_scorer |
all2 |
0.2 |
| bfcl_irrelevance |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_irrelevance |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_irrelevance |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
irrelevance_acc |
1.0 |
| bfcl_irrelevance |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_irrelevance |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
irrelevance_sterr |
0.0 |
| bfcl_irrelevance |
gemini-3.8-flash-openrouter |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_irrelevance |
gemini-3.8-flash |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_irrelevance |
gemini-3.8-flash |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_irrelevance |
gemini-3.8-flash |
default |
bfcl_scorer |
irrelevance_acc |
1.0 |
| bfcl_irrelevance |
gemini-3.8-flash |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_irrelevance |
gemini-3.8-flash |
default |
bfcl_scorer |
irrelevance_sterr |
0.0 |
| bfcl_irrelevance |
gemini-3.8-flash |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_irrelevance |
sonnet-5 |
default |
bfcl_scorer |
accuracy |
0.6 |
| bfcl_irrelevance |
sonnet-5 |
default |
bfcl_scorer |
stderr |
0.2 |
| bfcl_irrelevance |
sonnet-5 |
default |
bfcl_scorer |
irrelevance_acc |
0.6 |
| bfcl_irrelevance |
sonnet-5 |
default |
bfcl_scorer |
all |
0.6 |
| bfcl_irrelevance |
sonnet-5 |
default |
bfcl_scorer |
irrelevance_sterr |
0.2 |
| bfcl_irrelevance |
sonnet-5 |
default |
bfcl_scorer |
all2 |
0.2 |
| bfcl_irrelevance |
gpt-4.1 |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_irrelevance |
gpt-4.1 |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_irrelevance |
gpt-4.1 |
default |
bfcl_scorer |
irrelevance_acc |
1.0 |
| bfcl_irrelevance |
gpt-4.1 |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_irrelevance |
gpt-4.1 |
default |
bfcl_scorer |
irrelevance_sterr |
0.0 |
| bfcl_irrelevance |
gpt-4.1 |
default |
bfcl_scorer |
all2 |
0.0 |
| bfcl_irrelevance |
gpt-5.4-mini |
default |
bfcl_scorer |
accuracy |
1.0 |
| bfcl_irrelevance |
gpt-5.4-mini |
default |
bfcl_scorer |
stderr |
0.0 |
| bfcl_irrelevance |
gpt-5.4-mini |
default |
bfcl_scorer |
irrelevance_acc |
1.0 |
| bfcl_irrelevance |
gpt-5.4-mini |
default |
bfcl_scorer |
all |
1.0 |
| bfcl_irrelevance |
gpt-5.4-mini |
default |
bfcl_scorer |
irrelevance_sterr |
0.0 |
| bfcl_irrelevance |
gpt-5.4-mini |
default |
bfcl_scorer |
all2 |
0.0 |
| gpqa_diamond |
gemini-3.8-flash-openrouter |
default |
choice |
accuracy |
1.0 |
| gpqa_diamond |
gemini-3.8-flash-openrouter |
default |
choice |
stderr |
0.0 |
| gpqa_diamond |
gemini-3.8-flash |
default |
choice |
accuracy |
1.0 |
| gpqa_diamond |
gemini-3.8-flash |
default |
choice |
stderr |
0.0 |
| gpqa_diamond |
sonnet-5 |
default |
choice |
accuracy |
1.0 |
| gpqa_diamond |
sonnet-5 |
default |
choice |
stderr |
0.0 |
| gpqa_diamond |
gpt-4.1 |
default |
choice |
accuracy |
0.6 |
| gpqa_diamond |
gpt-4.1 |
default |
choice |
stderr |
0.2 |
| gpqa_diamond |
gpt-5.4-mini |
default |
choice |
accuracy |
0.8 |
| gpqa_diamond |
gpt-5.4-mini |
default |
choice |
stderr |
0.2 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge |
hle/accuracy |
0.6 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge |
hle/cerr |
0.4 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge1 |
hle/accuracy |
0.6 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge1 |
hle/cerr |
0.4 |
| hle |
gemini-3.8-flash-openrouter |
default |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge |
hle/accuracy |
0.8 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge |
hle/cerr |
0.1 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge1 |
hle/accuracy |
0.8 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge1 |
hle/cerr |
0.1 |
| hle |
gemini-3.8-flash |
default |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
sonnet-5 |
default |
hle/regex_judge |
hle/accuracy |
0.6 |
| hle |
sonnet-5 |
default |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
sonnet-5 |
default |
hle/regex_judge |
hle/cerr |
0.2 |
| hle |
sonnet-5 |
default |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
sonnet-5 |
default |
hle/regex_judge1 |
hle/accuracy |
0.6 |
| hle |
sonnet-5 |
default |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
sonnet-5 |
default |
hle/regex_judge1 |
hle/cerr |
0.2 |
| hle |
sonnet-5 |
default |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge |
hle/accuracy |
0.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge |
hle/stderr |
0.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge |
hle/cerr |
1.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge1 |
hle/accuracy |
0.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge1 |
hle/stderr |
0.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge1 |
hle/cerr |
1.0 |
| hle |
gpt-4.1 |
default |
hle/regex_judge1 |
hle/unscored |
0.0 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge |
hle/accuracy |
0.4 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge |
hle/stderr |
0.2 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge |
hle/cerr |
0.4 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge |
hle/unscored |
0.0 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge1 |
hle/accuracy |
0.4 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge1 |
hle/stderr |
0.2 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge1 |
hle/cerr |
0.4 |
| hle |
gpt-5.4-mini |
default |
hle/regex_judge1 |
hle/unscored |
0.0 |
| air_bench |
gemini-3.8-flash-openrouter |
default |
air_bench_scorer |
air_1 |
0.0 |
| air_bench |
gemini-3.8-flash-openrouter |
default |
air_bench_scorer |
air_1_1 |
0.0 |
| air_bench |
gemini-3.8-flash-openrouter |
default |
air_bench_scorer |
air_1_1_1 |
0.0 |
| air_bench |
gemini-3.8-flash-openrouter |
default |
air_bench_scorer |
all |
0.0 |
| air_bench |
sonnet-5 |
default |
air_bench_scorer |
air_1 |
0.0 |
| air_bench |
sonnet-5 |
default |
air_bench_scorer |
air_1_1 |
0.0 |
| air_bench |
sonnet-5 |
default |
air_bench_scorer |
air_1_1_1 |
0.0 |
| air_bench |
sonnet-5 |
default |
air_bench_scorer |
all |
0.0 |
| air_bench |
gpt-4.1 |
default |
air_bench_scorer |
air_1 |
1.0 |
| air_bench |
gpt-4.1 |
default |
air_bench_scorer |
air_1_1 |
1.0 |
| air_bench |
gpt-4.1 |
default |
air_bench_scorer |
air_1_1_1 |
1.0 |
| air_bench |
gpt-4.1 |
default |
air_bench_scorer |
all |
1.0 |
| air_bench |
gpt-5.4-mini |
default |
air_bench_scorer |
air_1 |
1.0 |
| air_bench |
gpt-5.4-mini |
default |
air_bench_scorer |
air_1_1 |
1.0 |
| air_bench |
gpt-5.4-mini |
default |
air_bench_scorer |
air_1_1_1 |
1.0 |
| air_bench |
gpt-5.4-mini |
default |
air_bench_scorer |
all |
1.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
50.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
100.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall |
40.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
50.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall) |
24.5 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
100.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
100.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall |
40.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_benign |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall) |
24.5 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
50.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall |
20.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
50.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall) |
20.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
100.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall |
20.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_benign |
gemini-3.8-flash |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall) |
20.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_benign |
sonnet-5 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
50.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall |
20.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
50.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall) |
20.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
100.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall |
20.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_benign |
gpt-4.1 |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall) |
20.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.DOMAIN__overall) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_benign |
gpt-5.4-mini |
default |
fortress_scorer_benign |
stderr(MetricLabel.ORS_LABEL__GroupKey.SUBDOMAIN__overall) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash-openrouter |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_adversarial |
gemini-3.8-flash |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
28.6 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall |
5.7 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall) |
5.7 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
28.6 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall |
5.7 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_adversarial |
sonnet-5 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall) |
5.7 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
35.7 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
64.3 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
85.7 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall |
57.1 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
21.4 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
7.1 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall) |
12.0 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
14.3 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud |
64.3 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
57.1 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
85.7 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall |
57.1 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
7.1 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_adversarial |
gpt-4.1 |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall) |
12.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities |
14.3 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) |
28.6 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall |
11.4 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Political Violence & Terrorism) |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Criminal & Financial Illicit Activities) |
14.3 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE)) |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.DOMAIN__overall) |
7.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud |
14.3 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD) |
28.6 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall |
11.4 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Illegal Weapons) |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Fraud) |
14.3 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Terrorism) |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__Radiological and Nuclear (WMD)) |
0.0 |
| fortress_adversarial |
gpt-5.4-mini |
default |
fortress_scorer_adversarial |
stderr(MetricLabel.ARS_LABEL__GroupKey.SUBDOMAIN__overall) |
7.0 |
| strong_reject |
gemini-3.8-flash-openrouter |
default |
strong_reject_scorer |
jailbreak_rate |
0.0 |
| strong_reject |
gemini-3.8-flash-openrouter |
default |
strong_reject_scorer |
strong_reject_metric |
0.0 |
| strong_reject |
gemini-3.8-flash |
default |
strong_reject_scorer |
jailbreak_rate |
0.0 |
| strong_reject |
gemini-3.8-flash |
default |
strong_reject_scorer |
strong_reject_metric |
0.0 |
| strong_reject |
sonnet-5 |
default |
strong_reject_scorer |
jailbreak_rate |
0.0 |
| strong_reject |
sonnet-5 |
default |
strong_reject_scorer |
strong_reject_metric |
0.0 |
| strong_reject |
gpt-4.1 |
default |
strong_reject_scorer |
jailbreak_rate |
0.0 |
| strong_reject |
gpt-4.1 |
default |
strong_reject_scorer |
strong_reject_metric |
0.0 |
| strong_reject |
gpt-5.4-mini |
default |
strong_reject_scorer |
jailbreak_rate |
0.0 |
| strong_reject |
gpt-5.4-mini |
default |
strong_reject_scorer |
strong_reject_metric |
0.0 |
| coconot |
gemini-3.8-flash-openrouter |
default |
model_graded_qa |
Requests with safety concerns |
20.0 |
| coconot |
gemini-3.8-flash-openrouter |
default |
model_graded_qa |
total |
20.0 |
| coconot |
gemini-3.8-flash |
default |
model_graded_qa |
Requests with safety concerns |
0.0 |
| coconot |
gemini-3.8-flash |
default |
model_graded_qa |
total |
0.0 |
| coconot |
sonnet-5 |
default |
model_graded_qa |
Requests with safety concerns |
0.0 |
| coconot |
sonnet-5 |
default |
model_graded_qa |
total |
0.0 |
| coconot |
gpt-4.1 |
default |
model_graded_qa |
Requests with safety concerns |
0.0 |
| coconot |
gpt-4.1 |
default |
model_graded_qa |
total |
0.0 |
| coconot |
gpt-5.4-mini |
default |
model_graded_qa |
Requests with safety concerns |
0.0 |
| coconot |
gpt-5.4-mini |
default |
model_graded_qa |
total |
0.0 |
| xstest_unsafe |
gemini-3.8-flash-openrouter |
default |
model_graded_qa |
refusal_rate |
80.0 |
| xstest_unsafe |
gemini-3.8-flash |
default |
model_graded_qa |
refusal_rate |
60.0 |
| xstest_unsafe |
sonnet-5 |
default |
model_graded_qa |
refusal_rate |
60.0 |
| xstest_unsafe |
gpt-4.1 |
default |
model_graded_qa |
refusal_rate |
80.0 |
| xstest_unsafe |
gpt-5.4-mini |
default |
model_graded_qa |
refusal_rate |
100.0 |
| xstest_safe |
gemini-3.8-flash-openrouter |
default |
model_graded_qa |
refusal_rate |
40.0 |
| xstest_safe |
gemini-3.8-flash |
default |
model_graded_qa |
refusal_rate |
0.0 |
| xstest_safe |
sonnet-5 |
default |
model_graded_qa |
refusal_rate |
0.0 |
| xstest_safe |
gpt-4.1 |
default |
model_graded_qa |
refusal_rate |
0.0 |
| xstest_safe |
gpt-5.4-mini |
default |
model_graded_qa |
refusal_rate |
20.0 |