Published task benchmark

Vendor Onboarding Agent

Validate identity, tax, banking, sanctions, and required documents; create or route the vendor record.

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

Finance, accounting, and procurement operationsAnalysisEvaluated 9/11/202699 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Vendor Onboarding Agent

Validate identity, tax, banking, sanctions, and required documents; create or route the vendor record.

Finance, accounting, and procurement operationsPer vendor
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
821 in · 780 out · 13.55s p50
$9.96 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
76%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
905 in · 930 out · 25.14s p50
$195 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.5275 input · $1.58 output /1M
OpenRouter · $2.00 input · $6.00 output /1M
80%
GPT-5.4
Hosted · Off-the-shelf
718 in · 1,314 out · 11.10s p50
$2151 /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
97%
Best accuracy
All 12 model results and methodology

Generated 99/100 examples — partial set accepted at the success threshold

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small69%99/99$32.14
Qwen3 235B A22Bmid71%99/99$233
DeepSeek V3mid74%99/99$80.35
Mistral Large 2407mid80%99/99$195
Arcee Trinity Large Thinkingmid70%99/99$121
GPT-5.4frontier97%99/99$2151
Claude Opus 4.7frontier91%99/99$4788
Gemini 3.1 Pro Previewfrontier59%99/99$2444
Gemma 4 E4B ITsmall76%99/99$9.96
Granite 4.1 8Bsmall60%99/99$10.89
Ministral 8B Instruct 2410small44%99/99$21.95
Qwen3 4B Instruct 2507small32%99/99$103

LLM-judge pass rate on 99 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-11T02:17:02.592Z.

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