Published task benchmark

Urgency-Sort

Ranks support tickets by sentiment and severity for immediate action.

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

Customer SupportAnalysisEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Urgency-Sort

Ranks support tickets by sentiment and severity for immediate action.

Customer SupportPer queue
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
637 in · 1,548 out · 9.97s p50
$39.43 /100K
AWS Bedrock temporary list price
View token rates
AWS Bedrock · $0.0600 input · $0.2300 output /1M
67%
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
606 in · 951 out · 15.42s p50
$201 /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
81%
GPT-5.4
Hosted · Off-the-shelf
560 in · 745 out · 7.77s p50
$1258 /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 v2small67%100/100$39.43
Qwen3 235B A22Bmid81%100/100$201
DeepSeek V3mid73%100/100$86.98
Mistral Large 2407mid77%100/100$148
Arcee Trinity Large Thinkingmid64%100/100$138
GPT-5.4frontier97%100/100$1258
Claude Opus 4.7frontier94%100/100$4034
Gemini 3.1 Pro Previewfrontier78%100/100$2124
Gemma 4 E4B ITsmall38%100/100$8.66
Granite 4.1 8Bsmall50%100/100$9.07
Ministral 8B Instruct 2410small58%100/100$19.44
Qwen3 4B Instruct 2507small55%100/100$84.88

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T10:02:02.755Z.

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