Published task benchmark

Profile-Builder

Maps resume text into structured JSON fields (skills, years, education) for ATS.

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

Profile-Builder

Maps resume text into structured JSON fields (skills, years, education) for ATS.

Document IntelligencePer resume
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
270 in · 185 out · 6.01s p50
$15.60 /100K
AWS Bedrock temporary proxy price
View token rates
AWS Bedrock · $0.1545 input · $0.6180 output /1M
10%
DeepSeek V3
Hosted · Off-the-shelf
253 in · 120 out · 0.97s p50
$19.81 /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
16%
GPT-5.4
Hosted · Off-the-shelf
247 in · 227 out · 2.08s p50
$402 /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
48%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small0%100/100$27.28
Qwen3 235B A22Bmid4%100/100$52.51
DeepSeek V3mid16%100/100$19.81
Mistral Large 2407mid12%100/100$60.98
Arcee Trinity Large Thinkingmid4%100/100$118
GPT-5.4frontier48%100/100$402
Claude Opus 4.7frontier21%100/100$1038
Gemini 3.1 Pro Previewfrontier10%100/100$1668
Gemma 4 E4B ITsmall4%100/100$3.11
Granite 4.1 8Bsmall5%100/100$3.52
Ministral 8B Instruct 2410small9%100/100$7.28
Qwen3 4B Instruct 2507small10%100/100$15.60

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T11:16:02.614Z.

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