Published task benchmark

Cash-Flow-Ref

Identifies recurring subscriptions and hidden fees in bank statement exports.

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

Document IntelligenceExtractionEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Extraction

Cash-Flow-Ref

Identifies recurring subscriptions and hidden fees in bank statement exports.

Document IntelligencePer statement
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Qwen3 4B Instruct 2507
4B · Off-the-shelf
771 in · 399 out · 15.33s p50
$36.57 /100K
AWS Bedrock temporary proxy price
View token rates
AWS Bedrock · $0.1545 input · $0.6180 output /1M
1%
Mistral Large 2407
123B · Off-the-shelf
814 in · 672 out · 17.88s p50
$149 /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
22%
GPT-5.4
Hosted · Off-the-shelf
664 in · 497 out · 3.12s p50
$912 /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
67%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small0%100/100$36.11
Qwen3 235B A22Bmid12%100/100$120
DeepSeek V3mid0%100/100$67.64
Mistral Large 2407mid22%100/100$149
Arcee Trinity Large Thinkingmid0%100/100$146
GPT-5.4frontier67%100/100$912
Claude Opus 4.7frontier20%100/100$2555
Gemini 3.1 Pro Previewfrontier37%100/100$2241
Gemma 4 E4B ITsmall0%100/100$4.34
Granite 4.1 8Bsmall0%100/100$7.04
Ministral 8B Instruct 2410small0%100/100$16.75
Qwen3 4B Instruct 2507small1%100/100$36.57

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T11:39:02.475Z.

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