Published task benchmark

SKU-Architect

Extracts product attributes (color, size, material) from supplier catalogs.

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

Document IntelligenceExtractionEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Extraction

SKU-Architect

Extracts product attributes (color, size, material) from supplier catalogs.

Document IntelligencePer catalog
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
215 in · 140 out · 1.26s p50
$1.93 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
44%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
204 in · 96 out · 0.97s p50
$15.90 /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
53%
GPT-5.4
Hosted · Off-the-shelf
198 in · 101 out · 1.35s p50
$201 /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
54%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small27%100/100$21.45
Qwen3 235B A22Bmid51%100/100$34.81
DeepSeek V3mid53%100/100$15.90
Mistral Large 2407mid34%100/100$39.77
Arcee Trinity Large Thinkingmid45%100/100$83.06
GPT-5.4frontier54%100/100$201
Claude Opus 4.7frontier45%100/100$715
Gemini 3.1 Pro Previewfrontier51%100/100$1216
Gemma 4 E4B ITsmall44%100/100$1.93
Granite 4.1 8Bsmall29%100/100$2.44
Ministral 8B Instruct 2410small25%100/100$5.57
Qwen3 4B Instruct 2507small35%100/100$12.00

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T15:42:02.650Z.

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