Published task benchmark

Prior-Art-AI

Compares a new invention description against existing patent abstracts for overlap.

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

Legal & ComplianceAnalysisEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Prior-Art-AI

Compares a new invention description against existing patent abstracts for overlap.

Legal & CompliancePer invention
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
554 in · 1,190 out · 20.07s p50
$13.72 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
81%
Best accuracyCheapest
DeepSeek V3
Hosted · Off-the-shelf
525 in · 996 out · 7.09s p50
$111 /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
64%
GPT-5.4
Hosted · Off-the-shelf
521 in · 1,928 out · 15.55s p50
$3022 /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
55%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small11%100/100$47.33
Qwen3 235B A22Bmid58%100/100$290
DeepSeek V3mid64%100/100$111
Mistral Large 2407mid25%100/100$263
Arcee Trinity Large Thinkingmid15%100/100$155
GPT-5.4frontier55%100/100$3022
Claude Opus 4.7frontier53%100/100$5264
Gemini 3.1 Pro Previewfrontier0%100/100$2503
Gemma 4 E4B ITsmall81%100/100$13.72
Granite 4.1 8Bsmall33%100/100$14.65
Ministral 8B Instruct 2410small18%100/100$29.14
Qwen3 4B Instruct 2507small30%100/100$117

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T09:07:02.431Z.

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