Analysis

Given loan terms and current financial statements, compute covenant ratios, compare them with thresholds, and flag current or near-term breaches.

Finance & AccountingPer loan

Not benchmarked

No result on this tier

Token profile pending

— /100K

Run this tier to add it

—

Nemotron Nano 9B v2

9B · Off-the-shelf

680 in · 1,809 out · 12.06s p50

$45.69 /100K

AWS Bedrock temporary list price

View token rates

AWS Bedrock · $0.0600 input · $0.2300 output /1M

31%

DeepSeek V3

Hosted · Off-the-shelf

572 in · 1,105 out · 9.83s p50

$123 /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

53%

GPT-5.4

Hosted · Off-the-shelf

551 in · 1,488 out · 12.08s p50

$2370 /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

54%

All 12 model results and methodology

Generated 100/100 examples

Model	Tier	Quality	Judged	Scenario cost
Nemotron Nano 9B v2	small	31%	100/100	$45.69
Qwen3 235B A22B	mid	43%	100/100	$313
DeepSeek V3	mid	53%	100/100	$123
Mistral Large 2407	mid	36%	100/100	$271
Arcee Trinity Large Thinking	mid	25%	100/100	$162
GPT-5.4	frontier	54%	100/100	$2370
Claude Opus 4.7	frontier	54%	100/100	$5394
Gemini 3.1 Pro Preview	frontier	3%	100/100	$2527
Gemma 4 E4B IT	small	25%	100/100	$17.95
Granite 4.1 8B	small	17%	100/100	$15.64
Ministral 8B Instruct 2410	small	9%	100/100	$28.07
Qwen3 4B Instruct 2507	small	16%	100/100	$118

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T08:58:02.679Z.

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?