Published task benchmark

Precedent-Finder

Summarizes the "Holding" and "Ratio Decidendi" of specific court judgments.

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

Legal & ComplianceSummarizationEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Summarization

Precedent-Finder

Summarizes the "Holding" and "Ratio Decidendi" of specific court judgments.

Legal & CompliancePer judgment
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
163 in · 121 out · 1.88s p50
$1.62 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
76%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
150 in · 257 out · 2.43s p50
$29.20 /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
91%
GPT-5.4
Hosted · Off-the-shelf
158 in · 355 out · 4.64s p50
$572 /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
99%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small49%100/100$17.43
Qwen3 235B A22Bmid82%100/100$95.87
DeepSeek V3mid91%100/100$29.20
Mistral Large 2407mid87%100/100$56.13
Arcee Trinity Large Thinkingmid91%100/100$48.35
GPT-5.4frontier99%100/100$572
Claude Opus 4.7frontier89%100/100$2897
Gemini 3.1 Pro Previewfrontier98%100/100$1660
Gemma 4 E4B ITsmall76%100/100$1.62
Granite 4.1 8Bsmall32%100/100$4.70
Ministral 8B Instruct 2410small44%100/100$5.05
Qwen3 4B Instruct 2507small28%100/100$28.23

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T09:14:02.641Z.

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