Ratio-Analyzer
Calculates and interprets key financial ratios (liquidity, profitability, leverage) from balance sheet data.
View token rates
Compare 2 router rates · observed 9/11/2026
Compare 2 router rates · observed 9/11/2026
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 85% | 100/100 | $15.61 |
| Qwen3 235B A22B | mid | 94% | 100/100 | $65.02 |
| DeepSeek V3 | mid | 89% | 100/100 | $25.95 |
| Mistral Large 2407 | mid | 96% | 100/100 | $63.30 |
| Arcee Trinity Large Thinking | mid | 89% | 100/100 | $55.37 |
| GPT-5.4 | frontier | 86% | 100/100 | $339 |
| Claude Opus 4.7 | frontier | 99% | 100/100 | $2219 |
| Gemini 3.1 Pro Preview | frontier | 100% | 100/100 | $1131 |
| Gemma 4 E4B IT | small | 70% | 100/100 | $3.73 |
| Granite 4.1 8B | small | 88% | 100/100 | $4.71 |
| Ministral 8B Instruct 2410 | small | 70% | 100/100 | $8.31 |
| Qwen3 4B Instruct 2507 | small | 97% | 100/100 | $28.20 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T14:06:03.197Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock