Classification
Expense-Code
Categorizes raw transactions into specific tax-deductible buckets.
Finance & AccountingPer transaction
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
168 in · 15 out · 0.29s p50
$0.5127 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
86%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
150 in · 18 out · 0.51s p50
$6.40 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.2900 input · $1.14 output /1M
TrustedRouter · $0.3376 input · $0.9390 output /1M
91%
GPT-5.4
Hosted · Off-the-shelf
150 in · 31 out · 1.36s p50
$84.00 /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
95%
Best accuracy
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 51% | 100/100 | $9.03 |
| Qwen3 235B A22B | mid | 76% | 100/100 | $14.20 |
| DeepSeek V3 | mid | 91% | 100/100 | $6.40 |
| Mistral Large 2407 | mid | 72% | 100/100 | $15.51 |
| Arcee Trinity Large Thinking | mid | 81% | 100/100 | $31.77 |
| GPT-5.4 | frontier | 95% | 100/100 | $84.00 |
| Claude Opus 4.7 | frontier | 84% | 100/100 | $280 |
| Gemini 3.1 Pro Preview | frontier | 79% | 100/100 | $583 |
| Gemma 4 E4B IT | small | 86% | 100/100 | $0.5127 |
| Granite 4.1 8B | small | 58% | 100/100 | $1.19 |
| Ministral 8B Instruct 2410 | small | 52% | 100/100 | $3.04 |
| Qwen3 4B Instruct 2507 | small | 59% | 100/100 | $5.07 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T20:26:02.523Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock