Published task benchmark

Substack-Sync

Summarizes a company's weekly activity into an engaging newsletter.

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

MarketingGenerationEvaluated 9/5/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Substack-Sync

Summarizes a company's weekly activity into an engaging newsletter.

MarketingPer newsletter
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Ministral 8B Instruct 2410
8B · Off-the-shelf
363 in · 388 out · 9.70s p50
$11.27 /100K
AWS Bedrock temporary proxy price
View token rates
AWS Bedrock · $0.1500 input · $0.1500 output /1M
77%
DeepSeek V3
Hosted · Off-the-shelf
347 in · 410 out · 3.13s p50
$50.21 /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
68%
GPT-5.4
Hosted · Off-the-shelf
339 in · 338 out · 3.04s p50
$592 /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
100%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small28%100/100$28.62
Qwen3 235B A22Bmid20%100/100$108
DeepSeek V3mid68%100/100$50.21
Mistral Large 2407mid56%100/100$97.27
Arcee Trinity Large Thinkingmid47%100/100$63.52
GPT-5.4frontier100%100/100$592
Claude Opus 4.7frontier84%100/100$2185
Gemini 3.1 Pro Previewfrontier93%100/100$2113
Gemma 4 E4B ITsmall75%100/100$6.51
Granite 4.1 8Bsmall68%100/100$5.96
Ministral 8B Instruct 2410small77%100/100$11.27
Qwen3 4B Instruct 2507small3%100/100$39.26

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-05T21:41:02.939Z.

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