BridgeBenchBridgeBench
Security
Model Analysis

Gemini 3.1 Pro

google/gemini-3.1-pro-preview

85.2

overall score

85.6% visible
82.2% hidden

Tasks

30

Passed

15

Failed

15

Avg latency

14038ms

Total cost

$0.2265

Domain Performance

Sanitization6 tasks
99.0
Auth & Session7 tasks
78.5
Access Control5 tasks
98.0
Detection & Analysis9 tasks
80.1
Traffic Protection1 tasks
95.6
Crypto Utils2 tasks
53.1

All Task Results

TaskDomainScore
sec-ssrf-detectorDetection & Analysis9.5
sec-crypto-utilsCrypto Utils10.0
sec-oauth-state-validatorAuth & Session10.0
sec-password-strengthAuth & Session49.0
sec-auth-log-anomaly-detectorDetection & Analysis62.2
sec-secret-detectorDetection & Analysis70.0
sec-csp-nonce-validatorDetection & Analysis88.3
sec-refresh-token-rotationAuth & Session91.5
sec-input-sanitizerSanitization93.7
sec-abac-rule-engineAccess Control94.2
sec-rate-limit-engineTraffic Protection95.6
sec-csp-parserDetection & Analysis96.1
sec-sql-injection-detectorDetection & Analysis96.1
sec-encryption-pipelineCrypto Utils96.2
sec-permission-checkerAccess Control97.3
sec-access-control-engineAccess Control99.5
sec-api-key-scope-checkerAccess Control99.5
sec-insecure-config-scannerDetection & Analysis99.5
sec-jwt-validatorAuth & Session99.5
sec-session-fixation-detectorAuth & Session99.5
sec-tenant-isolation-checkerAccess Control99.5
sec-vulnerability-scannerDetection & Analysis99.5
sec-cookie-policy-validatorAuth & Session100.0
sec-csrf-token-managerAuth & Session100.0
sec-dependency-risk-classifierDetection & Analysis100.0
sec-file-upload-validatorSanitization100.0
sec-hostname-allowlist-validatorSanitization100.0
sec-html-entity-encoderSanitization100.0
sec-safe-redirect-builderSanitization100.0
sec-url-sanitizerSanitization100.0

30tasks · Sorted by score (lowest first) · Hidden = adversarial edge case pass rate