Published task benchmark

Phishing Triage Agent

Inspect reported messages and telemetry, classify risk, contain artifacts, and notify affected users.

Compare measured quality, workload cost, and latency across model tiers. Results are task-specific and directional—not a general model ranking.

IT and security operationsClassificationEvaluated 9/11/2026100 evaluation examplesFallback pricing checked September 11, 2026
Classification

Phishing Triage Agent

Inspect reported messages and telemetry, classify risk, contain artifacts, and notify affected users.

IT and security operationsPer message
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Nemotron Nano 9B v2
9B · Off-the-shelf
679 in · 537 out · 4.04s p50
$16.43 /100K
AWS Bedrock temporary list price
View token rates
AWS Bedrock · $0.0600 input · $0.2300 output /1M
78%
Best accuracy
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
647 in · 48 out · 0.71s p50
$38.17 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.4550 input · $1.82 output /1M
TrustedRouter · $0.6330 input · $2.11 output /1M
76%
GPT-5.4
Hosted · Off-the-shelf
600 in · 49 out · 1.55s p50
$224 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $2.50 input · $15.00 output /1M
TrustedRouter · $2.64 input · $15.82 output /1M
75%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small78%100/100$16.43
Qwen3 235B A22Bmid76%100/100$38.17
DeepSeek V3mid66%100/100$18.23
Mistral Large 2407mid75%100/100$48.06
Arcee Trinity Large Thinkingmid59%100/100$88.94
GPT-5.4frontier75%100/100$224
Claude Opus 4.7frontier57%100/100$812
Gemini 3.1 Pro Previewfrontier43%100/100$787
Gemma 4 E4B ITsmall70%100/100$1.83
Granite 4.1 8Bsmall76%100/100$3.53
Ministral 8B Instruct 2410small67%100/100$11.03
Qwen3 4B Instruct 2507small74%100/100$15.81

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-11T05:58:03.763Z.

Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.

drydock

Have a neighboring workload?

Describe it in Task Explorer. If it is not measured yet, you can request a benchmark and follow future results.

Explore another task