Published task benchmark

RFP Executive Summary

Given an RFP and a structured response, summarize customer goals, mandatory requirements, differentiators, risks, and unresolved questions in one page.

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

Sales & MarketingSummarizationEvaluated 9/9/202696 evaluation examplesFallback pricing checked September 11, 2026
Summarization

RFP Executive Summary

Given an RFP and a structured response, summarize customer goals, mandatory requirements, differentiators, risks, and unresolved questions in one page.

Sales & MarketingPer rfp
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
954 in · 630 out · 16.52s p50
$23.76 /100K
AWS Bedrock temporary proxy price
View token rates
AWS Bedrock · $0.1500 input · $0.1500 output /1M
68%
DeepSeek V3
Hosted · Off-the-shelf
884 in · 645 out · 4.70s p50
$90.41 /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
78%
GPT-5.4
Hosted · Off-the-shelf
869 in · 960 out · 7.92s p50
$1657 /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 96/100 examples — partial set accepted at the success threshold

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small44%96/96$36.07
Qwen3 235B A22Bmid46%96/96$204
DeepSeek V3mid78%96/96$90.41
Mistral Large 2407mid74%96/96$165
Arcee Trinity Large Thinkingmid69%96/96$101
GPT-5.4frontier99%96/96$1657
Claude Opus 4.7frontier86%96/96$3915
Gemini 3.1 Pro Previewfrontier5%96/96$2579
Gemma 4 E4B ITsmall63%96/96$8.47
Granite 4.1 8Bsmall59%96/96$11.28
Ministral 8B Instruct 2410small68%96/96$23.76
Qwen3 4B Instruct 2507small48%96/96$58.57

LLM-judge pass rate on 96 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T04:04:02.479Z.

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