B2B Catalog Schema Mapping
Given a supplier spreadsheet sample and a target product schema, map source columns, propose type conversions, and identify unmapped required fields.
View token rates · observed 9/11/2026
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 | 2% | 100/100 | $50.90 |
| Qwen3 235B A22B | mid | 33% | 100/100 | $357 |
| DeepSeek V3 | mid | 56% | 100/100 | $164 |
| Mistral Large 2407 | mid | 33% | 100/100 | $268 |
| Arcee Trinity Large Thinking | mid | 11% | 100/100 | $176 |
| GPT-5.4 | frontier | 29% | 100/100 | $3181 |
| Claude Opus 4.7 | frontier | 53% | 100/100 | $5538 |
| Gemini 3.1 Pro Preview | frontier | 0% | 100/100 | $2560 |
| Gemma 4 E4B IT | small | 32% | 100/100 | $19.58 |
| Granite 4.1 8B | small | 16% | 100/100 | $14.74 |
| Ministral 8B Instruct 2410 | small | 2% | 100/100 | $30.38 |
| Qwen3 4B Instruct 2507 | small | 4% | 100/100 | $136 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T11:38:02.484Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock