Classification
Patient Satisfaction Complaint Classification
Given survey comments and a supplied service taxonomy, classify wait time, communication, access, billing, facility, or care-quality concerns.
Healthcare & Life SciencesPer survey
Not benchmarked
No result on this tier
Token profile pending
— /100K
Run this tier to add it
—
Qwen3 4B Instruct 2507
4B · Off-the-shelf
278 in · 44 out · 2.00s p50
$7.01 /100K
AWS Bedrock temporary proxy price
View token rates
AWS Bedrock · $0.1545 input · $0.6180 output /1M
97%
Mistral Large 2407
123B · Off-the-shelf
319 in · 34 out · 1.22s p50
$22.21 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.5275 input · $1.58 output /1M
OpenRouter · $2.00 input · $6.00 output /1M
99%
GPT-5.4
Hosted · Off-the-shelf
270 in · 34 out · 1.32s p50
$119 /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
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 86% | 100/100 | $11.05 |
| Qwen3 235B A22B | mid | 98% | 100/100 | $20.48 |
| DeepSeek V3 | mid | 97% | 100/100 | $11.05 |
| Mistral Large 2407 | mid | 99% | 100/100 | $22.21 |
| Arcee Trinity Large Thinking | mid | 97% | 100/100 | $62.24 |
| GPT-5.4 | frontier | 100% | 100/100 | $119 |
| Claude Opus 4.7 | frontier | 100% | 100/100 | $399 |
| Gemini 3.1 Pro Preview | frontier | 98% | 100/100 | $603 |
| Gemma 4 E4B IT | small | 95% | 100/100 | $0.8292 |
| Granite 4.1 8B | small | 94% | 100/100 | $1.77 |
| Ministral 8B Instruct 2410 | small | 89% | 100/100 | $4.83 |
| Qwen3 4B Instruct 2507 | small | 97% | 100/100 | $7.01 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T08:20:03.202Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock