Extraction

Extracts vendor names, dates, amounts, and VAT numbers from unstructured PDFs.

Finance & AccountingPer invoice

Not benchmarked

No result on this tier

Token profile pending

— /100K

Run this tier to add it

—

Granite 4.1 8B

8B · Off-the-shelf

264 in · 133 out · 1.80s p50

$2.65 /100K

Best current price · OpenRouter

Compare 2 router rates · observed 9/4/2026

OpenRouter · $0.0500 input · $0.1000 output /1M

TrustedRouter · $0.0527 input · $0.1055 output /1M

63%

Mistral Large 2407

123B · Off-the-shelf

326 in · 128 out · 2.99s p50

$37.45 /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

49%

Claude Opus 4.7

Hosted · Off-the-shelf

395 in · 244 out · 2.77s p50

$808 /100K

Best current price · OpenRouter

Compare 2 router rates · observed 9/11/2026

OpenRouter · $5.00 input · $25.00 output /1M

TrustedRouter · $5.28 input · $26.38 output /1M

79%

Best accuracy

All 12 model results and methodology

Generated 100/100 examples

Model	Tier	Quality	Judged	Scenario cost
Nemotron Nano 9B v2	small	32%	100/100	$26.25
Qwen3 235B A22B	mid	18%	100/100	$36.17
DeepSeek V3	mid	8%	100/100	$13.69
Mistral Large 2407	mid	49%	100/100	$37.45
Arcee Trinity Large Thinking	mid	22%	100/100	$50.78
GPT-5.4	frontier	69%	100/100	$200
Claude Opus 4.7	frontier	79%	100/100	$808
Gemini 3.1 Pro Preview	frontier	50%	100/100	$714
Gemma 4 E4B IT	small	4%	100/100	$1.45
Granite 4.1 8B	small	63%	100/100	$2.65
Ministral 8B Instruct 2410	small	49%	100/100	$6.00
Qwen3 4B Instruct 2507	small	17%	100/100	$17.66

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T20:32:02.258Z.

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?