Published task benchmark

Rec-Engine

Matches bank statements to internal records and explains discrepancies.

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

Finance & AccountingAnalysisEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Rec-Engine

Matches bank statements to internal records and explains discrepancies.

Finance & AccountingPer statement
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
1,015 in · 1,356 out · 19.69s p50
$18.64 /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
11%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
1,057 in · 1,313 out · 12.44s p50
$159 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.3376 input · $0.9390 output /1M
OpenRouter · $0.2900 input · $1.14 output /1M
28%
GPT-5.4
Hosted · Off-the-shelf
1,010 in · 1,824 out · 16.28s p50
$2989 /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
53%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small10%100/100$52.15
Qwen3 235B A22Bmid26%100/100$392
DeepSeek V3mid28%100/100$159
Mistral Large 2407mid25%100/100$347
Arcee Trinity Large Thinkingmid4%100/100$183
GPT-5.4frontier53%100/100$2989
Claude Opus 4.7frontier42%100/100$5690
Gemini 3.1 Pro Previewfrontier0%100/100$2641
Gemma 4 E4B ITsmall10%100/100$18.66
Granite 4.1 8Bsmall11%100/100$18.64
Ministral 8B Instruct 2410small6%100/100$43.11
Qwen3 4B Instruct 2507small9%100/100$139

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T09:15:02.615Z.

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