Published task benchmark

Legal-Template

Generates first drafts of simple contracts (Service Agreements, LoIs) from basic terms.

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

Legal & ComplianceGenerationEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Legal-Template

Generates first drafts of simple contracts (Service Agreements, LoIs) from basic terms.

Legal & CompliancePer contract
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
429 in · 992 out · 15.43s p50
$11.37 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
49%
Mistral Large 2407
123B · Off-the-shelf
473 in · 851 out · 22.57s p50
$160 /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
36%
GPT-5.4
Hosted · Off-the-shelf
396 in · 1,102 out · 9.50s p50
$1752 /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
77%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small0%100/100$42.96
Qwen3 235B A22Bmid1%100/100$304
DeepSeek V3mid23%100/100$117
Mistral Large 2407mid36%100/100$160
Arcee Trinity Large Thinkingmid2%100/100$144
GPT-5.4frontier77%100/100$1752
Claude Opus 4.7frontier6%100/100$5285
Gemini 3.1 Pro Previewfrontier2%100/100$2478
Gemma 4 E4B ITsmall49%100/100$11.37
Granite 4.1 8Bsmall15%100/100$10.07
Ministral 8B Instruct 2410small7%100/100$36.06
Qwen3 4B Instruct 2507small0%100/100$103

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T09:51:03.057Z.

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