Generation
ADR-Writer
Records why a decision was made to prevent "we already tried that" syndrome later.
People ManagementPer decision
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
365 in · 340 out · 5.22s p50
$4.36 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
98%
Best accuracyCheapest
Mistral Large 2407
123B · Off-the-shelf
399 in · 578 out · 15.22s p50
$113 /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
97%
GPT-5.4
Hosted · Off-the-shelf
345 in · 408 out · 4.78s p50
$698 /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
98%
Best accuracy
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 74% | 100/100 | $21.49 |
| Qwen3 235B A22B | mid | 68% | 100/100 | $80.85 |
| DeepSeek V3 | mid | 92% | 100/100 | $52.59 |
| Mistral Large 2407 | mid | 97% | 100/100 | $113 |
| Arcee Trinity Large Thinking | mid | 71% | 100/100 | $60.73 |
| GPT-5.4 | frontier | 98% | 100/100 | $698 |
| Claude Opus 4.7 | frontier | 95% | 100/100 | $2691 |
| Gemini 3.1 Pro Preview | frontier | 96% | 100/100 | $1916 |
| Gemma 4 E4B IT | small | 98% | 100/100 | $4.36 |
| Granite 4.1 8B | small | 91% | 100/100 | $8.29 |
| Ministral 8B Instruct 2410 | small | 96% | 100/100 | $13.57 |
| Qwen3 4B Instruct 2507 | small | 54% | 100/100 | $28.63 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T20:39:02.587Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock