Published task benchmark

Conflict-Check

Scans firm-wide client lists to flag potential conflicts of interest for new matters.

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

Conflict-Check

Scans firm-wide client lists to flag potential conflicts of interest for new matters.

Legal & CompliancePer matter
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
709 in · 750 out · 12.02s p50
$9.41 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
64%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
804 in · 1,039 out · 29.75s p50
$207 /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
67%
GPT-5.4
Hosted · Off-the-shelf
646 in · 1,450 out · 13.20s p50
$2337 /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
97%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small34%100/100$42.65
Qwen3 235B A22Bmid58%100/100$273
DeepSeek V3mid66%100/100$91.50
Mistral Large 2407mid67%100/100$207
Arcee Trinity Large Thinkingmid50%100/100$141
GPT-5.4frontier97%100/100$2337
Claude Opus 4.7frontier31%100/100$5557
Gemini 3.1 Pro Previewfrontier18%100/100$2521
Gemma 4 E4B ITsmall64%100/100$9.41
Granite 4.1 8Bsmall42%100/100$11.62
Ministral 8B Instruct 2410small16%100/100$17.10
Qwen3 4B Instruct 2507small14%100/100$121

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T09:06:38.203Z.

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