Published task benchmark

Constrained Ad-Copy Variant Generation

Given a product brief, audience, channel limits, and prohibited claims, generate diverse ad variants that satisfy length and compliance rules.

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

Sales & MarketingGenerationEvaluated 9/9/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Constrained Ad-Copy Variant Generation

Given a product brief, audience, channel limits, and prohibited claims, generate diverse ad variants that satisfy length and compliance rules.

Sales & MarketingPer ad
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
350 in · 326 out · 5.14s p50
$4.18 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
22%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
336 in · 244 out · 2.09s p50
$34.25 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.3376 input · $0.9390 output /1M
OpenRouter · $0.2900 input · $1.14 output /1M
19%
GPT-5.4
Hosted · Off-the-shelf
326 in · 283 out · 3.18s p50
$506 /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
83%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small7%100/100$31.57
Qwen3 235B A22Bmid5%100/100$74.48
DeepSeek V3mid19%100/100$34.25
Mistral Large 2407mid13%100/100$83.34
Arcee Trinity Large Thinkingmid16%100/100$81.86
GPT-5.4frontier83%100/100$506
Claude Opus 4.7frontier79%100/100$1939
Gemini 3.1 Pro Previewfrontier40%100/100$2197
Gemma 4 E4B ITsmall22%100/100$4.18
Granite 4.1 8Bsmall5%100/100$5.16
Ministral 8B Instruct 2410small5%100/100$10.70
Qwen3 4B Instruct 2507small1%100/100$28.69

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T03:12:02.527Z.

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