Published task benchmark

Corporate Minutes Public Redaction

Given synthetic board minutes and a redaction policy, remove personal data and confidential strategy while preserving motions, votes, and publishable governance facts.

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

Legal & ComplianceGenerationEvaluated 9/8/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Corporate Minutes Public Redaction

Given synthetic board minutes and a redaction policy, remove personal data and confidential strategy while preserving motions, votes, and publishable governance facts.

Legal & CompliancePer minutes
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Nemotron Nano 9B v2
9B · Off-the-shelf
796 in · 1,600 out · 10.22s p50
$41.58 /100K
AWS Bedrock temporary list price
View token rates
AWS Bedrock · $0.0600 input · $0.2300 output /1M
16%
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
778 in · 525 out · 8.84s p50
$131 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.4550 input · $1.82 output /1M
TrustedRouter · $0.6330 input · $2.11 output /1M
41%
Claude Opus 4.7
Hosted · Off-the-shelf
1,271 in · 800 out · 7.31s p50
$2636 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $5.00 input · $25.00 output /1M
TrustedRouter · $5.28 input · $26.38 output /1M
64%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small16%100/100$41.58
Qwen3 235B A22Bmid41%100/100$131
DeepSeek V3mid38%100/100$60.91
Mistral Large 2407mid29%100/100$128
Arcee Trinity Large Thinkingmid26%100/100$88.28
GPT-5.4frontier62%100/100$782
Claude Opus 4.7frontier64%100/100$2636
Gemini 3.1 Pro Previewfrontier7%100/100$2533
Gemma 4 E4B ITsmall9%100/100$6.23
Granite 4.1 8Bsmall10%100/100$8.86
Ministral 8B Instruct 2410small5%100/100$19.00
Qwen3 4B Instruct 2507small14%100/100$48.17

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-08T21:03:02.952Z.

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