Cases

Four real runs on public datasets: a fine-tuned small model against Claude, GPT and Gemini on the same held-out examples, with latency, cost and run time.

• Support routing: 100% on 294 held-out tickets

  A fine-tuned GLM 5.3 Flash routed customer messages to the right intent on every held-out ticket, against 95.9% for Claude Sonnet 5.5 and 90.5% for Claude Haiku 5.5.

• Receipt extraction: 71.1% field accuracy against 51.6% for Sonnet

  A fine-tuned gpt-oss 20B turned receipts into JSON more accurately than Claude Sonnet 5.5, GPT-6 Luna and Gemini 3.8 Flash, at $0.124 per 1,000 documents.

• Comment moderation: 74.7% accuracy against 44.4% for the best prompted model

  A fine-tuned gpt-oss 20B learned the raters’ threshold on Civil Comments and sorted comments into allow, review and remove far better than prompted frontier models.

• Distillation: a student that matches its teacher, 2.6× faster

  A gpt-oss 20B trained on DeepSeek V4.1 Flash support answers scored 77.5% against the teacher’s 76.7%, with a median latency of 795 ms against 2,082 ms.