Classification

Given a student profile and supplied scholarship rules, classify eligibility, show each satisfied or unmet criterion, and flag ambiguous evidence.

Education & EdTechPer application

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

548 in · 737 out · 4.05s p50

$20.24 /100K

AWS Bedrock temporary list price

View token rates

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

55%

DeepSeek V3

Hosted · Off-the-shelf

513 in · 162 out · 1.90s p50

$32.53 /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

55%

GPT-5.4

Hosted · Off-the-shelf

498 in · 399 out · 4.10s p50

$723 /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

90%

Best accuracy

All 12 model results and methodology

Generated 100/100 examples

Model	Tier	Quality	Judged	Scenario cost
Nemotron Nano 9B v2	small	55%	100/100	$20.24
Qwen3 235B A22B	mid	24%	100/100	$37.31
DeepSeek V3	mid	55%	100/100	$32.53
Mistral Large 2407	mid	24%	100/100	$59.82
Arcee Trinity Large Thinking	mid	40%	100/100	$143
GPT-5.4	frontier	90%	100/100	$723
Claude Opus 4.7	frontier	89%	100/100	$1200
Gemini 3.1 Pro Preview	frontier	85%	100/100	$1428
Gemma 4 E4B IT	small	19%	100/100	$1.96
Granite 4.1 8B	small	15%	100/100	$3.31
Ministral 8B Instruct 2410	small	4%	100/100	$9.55
Qwen3 4B Instruct 2507	small	32%	100/100	$21.38

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T09:48:02.951Z.

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?