Published task benchmark

Customs HS Code Classifier

Assign Harmonized System (HS) codes to product descriptions.

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

Legal & ComplianceClassificationEvaluated 9/4/2026100 evaluation examplesFallback pricing checked September 11, 2026
Classification

Customs HS Code Classifier

Assign Harmonized System (HS) codes to product descriptions.

Legal & CompliancePer product
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
158 in · 67 out · 0.89s p50
$1.04 /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
140 in · 102 out · 4.38s p50
$14.30 /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
86%
GPT-5.4
Hosted · Off-the-shelf
142 in · 87 out · 1.93s p50
$166 /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
98%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small15%100/100$15.75
Qwen3 235B A22Bmid70%100/100$29.44
DeepSeek V3mid86%100/100$14.30
Mistral Large 2407mid71%100/100$27.17
Arcee Trinity Large Thinkingmid27%100/100$85.84
GPT-5.4frontier98%100/100$166
Claude Opus 4.7frontier95%100/100$1065
Gemini 3.1 Pro Previewfrontier92%100/100$1034
Gemma 4 E4B ITsmall44%100/100$1.04
Granite 4.1 8Bsmall1%100/100$2.24
Ministral 8B Instruct 2410small9%100/100$5.21
Qwen3 4B Instruct 2507small7%100/100$13.27

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T19:20:03.226Z.

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