Analysis
Counterfeit Listing Detection
Given an authorized product record and a marketplace listing, flag suspicious brand, image-description, price, seller, and identifier discrepancies.
E-commerce & LogisticsPer listing
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
636 in · 989 out · 14.83s p50
$11.78 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
92%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
703 in · 900 out · 25.41s p50
$180 /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
92%
GPT-5.4
Hosted · Off-the-shelf
552 in · 1,593 out · 15.62s p50
$2528 /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
99%
Best accuracy
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 57% | 100/100 | $44.54 |
| Qwen3 235B A22B | mid | 82% | 100/100 | $284 |
| DeepSeek V3 | mid | 85% | 100/100 | $108 |
| Mistral Large 2407 | mid | 92% | 100/100 | $180 |
| Arcee Trinity Large Thinking | mid | 78% | 100/100 | $124 |
| GPT-5.4 | frontier | 99% | 100/100 | $2528 |
| Claude Opus 4.7 | frontier | 76% | 100/100 | $5311 |
| Gemini 3.1 Pro Preview | frontier | 18% | 100/100 | $2511 |
| Gemma 4 E4B IT | small | 92% | 100/100 | $11.78 |
| Granite 4.1 8B | small | 76% | 100/100 | $14.40 |
| Ministral 8B Instruct 2410 | small | 57% | 100/100 | $22.29 |
| Qwen3 4B Instruct 2507 | small | 40% | 100/100 | $111 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T08:46:02.439Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock