Classification
Email Unsubscribe Reason Classification
Given unsubscribe comments, assign one supplied reason label per response and use the fallback for ambiguous or irrelevant feedback.
Sales & MarketingPer feedback
Not benchmarked
No result on this tier
Token profile pending
— /100K
Run this tier to add it
—
Gemma 4 E4B IT
E4B · Off-the-shelf
199 in · 22 out · 0.39s p50
$0.6520 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
99%
Cheapest
Arcee Trinity Large Thinking
400B · Off-the-shelf
190 in · 378 out · 0.87s p50
$34.99 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.2500 input · $0.8000 output /1M
TrustedRouter · $0.2638 input · $0.8440 output /1M
99%
Claude Opus 4.7
Hosted · Off-the-shelf
336 in · 58 out · 1.73s p50
$313 /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
100%
Best accuracy
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 98% | 100/100 | $7.10 |
| Qwen3 235B A22B | mid | 96% | 100/100 | $15.88 |
| DeepSeek V3 | mid | 93% | 100/100 | $7.99 |
| Mistral Large 2407 | mid | 97% | 100/100 | $16.72 |
| Arcee Trinity Large Thinking | mid | 99% | 100/100 | $34.99 |
| GPT-5.4 | frontier | 99% | 100/100 | $94.25 |
| Claude Opus 4.7 | frontier | 100% | 100/100 | $313 |
| Gemini 3.1 Pro Preview | frontier | 100% | 100/100 | $564 |
| Gemma 4 E4B IT | small | 99% | 100/100 | $0.6520 |
| Granite 4.1 8B | small | 95% | 100/100 | $1.30 |
| Ministral 8B Instruct 2410 | small | 91% | 100/100 | $3.42 |
| Qwen3 4B Instruct 2507 | small | 94% | 100/100 | $5.52 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T02:47:02.690Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock