Published task benchmark

Opportunity Hygiene Agent

Detect stale or inconsistent opportunities and apply permitted stage, date, and next-step corrections.

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

Sales and revenue operationsAnalysisEvaluated 9/11/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Opportunity Hygiene Agent

Detect stale or inconsistent opportunities and apply permitted stage, date, and next-step corrections.

Sales and revenue operationsPer opportunity
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Gemma 4 E4B IT
E4B · Off-the-shelf
669 in · 1,042 out · 16.43s p50
$12.40 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
21%
DeepSeek V3
Hosted · Off-the-shelf
594 in · 842 out · 17.77s p50
$99.05 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.2500 input · $1.00 output /1M
TrustedRouter · $0.3376 input · $0.9390 output /1M
50%
Claude Opus 4.7
Hosted · Off-the-shelf
954 in · 1,405 out · 16.70s p50
$3990 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $5.00 input · $25.00 output /1M
TrustedRouter · $5.28 input · $26.38 output /1M
82%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small10%100/100$43.91
Qwen3 235B A22Bmid42%100/100$266
DeepSeek V3mid50%100/100$99.05
Mistral Large 2407mid18%100/100$204
Arcee Trinity Large Thinkingmid17%100/100$158
GPT-5.4frontier58%100/100$1516
Claude Opus 4.7frontier82%100/100$3990
Gemini 3.1 Pro Previewfrontier26%100/100$2474
Gemma 4 E4B ITsmall21%100/100$12.40
Granite 4.1 8Bsmall10%100/100$11.65
Ministral 8B Instruct 2410small4%100/100$26.19
Qwen3 4B Instruct 2507small5%100/100$125

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-11T10:30:03.771Z.

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