Generation
Query-Tune
Refactors slow SQL queries into performant ones for specific databases.
Developer ToolsPer query
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
357 in · 124 out · 1.93s p50
$2.06 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
75%
Cheapest
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
318 in · 459 out · 4.28s p50
$98.01 /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
79%
GPT-5.4
Hosted · Off-the-shelf
310 in · 129 out · 1.43s p50
$271 /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
95%
Best accuracy
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 49% | 100/100 | $35.88 |
| Qwen3 235B A22B | mid | 79% | 100/100 | $98.01 |
| DeepSeek V3 | mid | 72% | 100/100 | $36.70 |
| Mistral Large 2407 | mid | 69% | 100/100 | $85.77 |
| Arcee Trinity Large Thinking | mid | 12% | 100/100 | $160 |
| GPT-5.4 | frontier | 95% | 100/100 | $271 |
| Claude Opus 4.7 | frontier | 82% | 100/100 | $2135 |
| Gemini 3.1 Pro Preview | frontier | 72% | 100/100 | $1742 |
| Gemma 4 E4B IT | small | 75% | 100/100 | $2.06 |
| Granite 4.1 8B | small | 62% | 100/100 | $5.37 |
| Ministral 8B Instruct 2410 | small | 33% | 100/100 | $9.49 |
| Qwen3 4B Instruct 2507 | small | 58% | 100/100 | $49.66 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-05T22:20:02.641Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock