Instruction Following Benchmark

SGD/SGD-X

Schema-Guided Dialogue (SGD) evaluated with SGD-X robustness prompts, scored as macro-F1 on a 0-100 scale in Cloudflare's internal Decision Index 0.2.1 suite.

Category

Instruction Following

Score type

percent

Scale

100%

higher is better

Models tested

2

What is SGD/SGD-X?

SGD/SGD-X is a benchmark for how precisely a model obeys the instructions it was given. The official description says: "Schema-Guided Dialogue (SGD) evaluated with SGD-X robustness prompts, scored as macro-F1 on a 0-100 scale in Cloudflare's internal Decision Index 0.2.1 suite". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

SGD/SGD-X measures how precisely a model obeys the instructions it was given. In detail, it checks:

  • meeting verifiable constraints (length, format, language, layout)
  • following several constraints correctly at once
  • keeping the constraints over long, multi-turn conversations
  • not ignoring parts of the instruction while sounding plausible

How to read the score

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Schema-Guided Dialogue (SGD) evaluated with SGD-X robustness prompts, scored as macro-F1 on a 0-100 scale in Cloudflare's internal Decision Index 0.2.1 suite.

Frequently asked questions

What is the SGD/SGD-X benchmark?

SGD/SGD-X is a benchmark for how precisely a model obeys the instructions it was given. The official description says: 'Schema-Guided Dialogue (SGD) evaluated with SGD-X robustness prompts, scored as macro-F1 on a 0-100 scale in Cloudflare's internal Decision Index 0.2.1 suite'. Below we describe in simple words what benchmarks of this type generally examine.

What does SGD/SGD-X test?

SGD/SGD-X mainly measures how precisely a model obeys the instructions it was given. Concretely, it checks: meeting verifiable constraints (length, format, language, layout); following several constraints correctly at once; keeping the constraints over long, multi-turn conversations.

How is the SGD/SGD-X score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get SGD/SGD-X data and scores?

The official source is https://clef-evals.workers-ai-mle.workers.dev/. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/sgd-sgd-x/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 2 models tested

Reset
# Model Score Date Source Verified
1 Clef
Cloudflare
43.8%
— Report Verified
2 Clef-Flash
Cloudflare
34.2%
— Report Verified

What now?

You've seen how models score on SGD/SGD-X — here's what to do next.