Chapter Glossary Extraction
Given a textbook chapter, extract domain terms, source-grounded definitions, and the section in which each term is introduced.
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 | 4% | 100/100 | $31.85 |
| Qwen3 235B A22B | mid | 15% | 100/100 | $111 |
| DeepSeek V3 | mid | 34% | 100/100 | $57.90 |
| Mistral Large 2407 | mid | 19% | 100/100 | $118 |
| Arcee Trinity Large Thinking | mid | 20% | 100/100 | $106 |
| GPT-5.4 | frontier | 43% | 100/100 | $916 |
| Claude Opus 4.7 | frontier | 30% | 100/100 | $2264 |
| Gemini 3.1 Pro Preview | frontier | 31% | 100/100 | $2105 |
| Gemma 4 E4B IT | small | 43% | 100/100 | $6.71 |
| Granite 4.1 8B | small | 9% | 100/100 | $7.11 |
| Ministral 8B Instruct 2410 | small | 12% | 100/100 | $12.88 |
| Qwen3 4B Instruct 2507 | small | 3% | 100/100 | $35.95 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T09:59:02.938Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock