Published task benchmark

Growth-Index

Identifies when a customer’s usage patterns suggest they need a higher tier.

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

Customer SuccessAnalysisEvaluated 9/4/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Growth-Index

Identifies when a customer’s usage patterns suggest they need a higher tier.

Customer SuccessPer account
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Granite 4.1 8B
8B · Off-the-shelf
246 in · 692 out · 8.84s p50
$8.15 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/4/2026
OpenRouter · $0.0500 input · $0.1000 output /1M
TrustedRouter · $0.0527 input · $0.1055 output /1M
89%
DeepSeek V3
Hosted · Off-the-shelf
249 in · 448 out · 3.40s p50
$50.47 /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
94%
Claude Opus 4.7
Hosted · Off-the-shelf
391 in · 1,146 out · 15.11s p50
$3061 /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
99%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small80%100/100$21.36
Qwen3 235B A22Bmid82%100/100$108
DeepSeek V3mid94%100/100$50.47
Mistral Large 2407mid89%100/100$109
Arcee Trinity Large Thinkingmid77%100/100$65.03
GPT-5.4frontier98%100/100$849
Claude Opus 4.7frontier99%100/100$3061
Gemini 3.1 Pro Previewfrontier88%100/100$1667
Gemma 4 E4B ITsmall79%100/100$7.01
Granite 4.1 8Bsmall89%100/100$8.15
Ministral 8B Instruct 2410small34%100/100$11.47
Qwen3 4B Instruct 2507small20%100/100$85.07

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T23:20:02.582Z.

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