Published task benchmark

Risk-Evaluator

Analyzes loan applications for qualitative risk factors not seen in numbers.

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

InvestmentAnalysisEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Risk-Evaluator

Analyzes loan applications for qualitative risk factors not seen in numbers.

InvestmentPer application
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
525 in · 989 out · 15.73s p50
$11.54 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
96%
Best accuracyCheapest
Mistral Large 2407
123B · Off-the-shelf
586 in · 1,110 out · 30.69s p50
$207 /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
95%
GPT-5.4
Hosted · Off-the-shelf
482 in · 1,747 out · 21.85s p50
$2741 /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
80%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small33%100/100$42.72
Qwen3 235B A22Bmid61%100/100$262
DeepSeek V3mid77%100/100$93.71
Mistral Large 2407mid95%100/100$207
Arcee Trinity Large Thinkingmid74%100/100$123
GPT-5.4frontier80%100/100$2741
Claude Opus 4.7frontier43%100/100$5344
Gemini 3.1 Pro Previewfrontier23%100/100$2485
Gemma 4 E4B ITsmall96%100/100$11.54
Granite 4.1 8Bsmall68%100/100$13.37
Ministral 8B Instruct 2410small65%100/100$24.02
Qwen3 4B Instruct 2507small21%100/100$120

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T12:29:02.283Z.

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