Published task benchmark

Rent-Logic

Extracts key dates, rent amounts, and escalation clauses from commercial leases.

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

Rent-Logic

Extracts key dates, rent amounts, and escalation clauses from commercial leases.

Document IntelligencePer lease
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
496 in · 341 out · 5.16s p50
$4.64 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
34%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
452 in · 271 out · 2.94s p50
$40.71 /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
35%
GPT-5.4
Hosted · Off-the-shelf
436 in · 336 out · 2.44s p50
$613 /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
52%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small12%100/100$28.62
Qwen3 235B A22Bmid26%100/100$79.17
DeepSeek V3mid35%100/100$40.71
Mistral Large 2407mid26%100/100$96.53
Arcee Trinity Large Thinkingmid15%100/100$87.27
GPT-5.4frontier52%100/100$613
Claude Opus 4.7frontier39%100/100$1520
Gemini 3.1 Pro Previewfrontier40%100/100$1885
Gemma 4 E4B ITsmall34%100/100$4.64
Granite 4.1 8Bsmall21%100/100$5.11
Ministral 8B Instruct 2410small2%100/100$11.54
Qwen3 4B Instruct 2507small3%100/100$26.08

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T10:48:02.815Z.

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