ACOS
ACOS: aspect-category-opinion-sentiment quad classification over reviews, scored as per-review F1 on a 0-100 scale in Cloudflare's internal Decision Index 0.2.1 suite.
Category
General Capabilities
Score type
percent
Scale
100%
higher is better
Models tested
2
What is ACOS?
ACOS is a benchmark for broad everyday usefulness across domains. The official description says: "ACOS: aspect-category-opinion-sentiment quad classification over reviews, scored as per-review 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?
ACOS measures broad everyday usefulness across domains. In detail, it checks:
- realistic, open-ended requests from varied professional fields
- correct, well-structured and helpful responses
- consistent quality across very different task types
- judgement and advice quality, not just factual recall
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: ACOS: aspect-category-opinion-sentiment quad classification over reviews, scored as per-review F1 on a 0-100 scale in Cloudflare's internal Decision Index 0.2.1 suite.
Frequently asked questions
What is the ACOS benchmark?
ACOS is a benchmark for broad everyday usefulness across domains. The official description says: 'ACOS: aspect-category-opinion-sentiment quad classification over reviews, scored as per-review 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 ACOS test?
ACOS mainly measures broad everyday usefulness across domains. Concretely, it checks: realistic, open-ended requests from varied professional fields; correct, well-structured and helpful responses; consistent quality across very different task types.
How is the ACOS 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 ACOS 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/acos/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Official benchmark page / paper
The benchmark maintainer's website, paper or leaderboard
Benchmark metadata (JSON)
This page's benchmark record from the Open LLM Radar API
All model scores (JSON download)
Full score table as JSON; paginate with limit/offset params
Open LLM Radar API docs
Swagger UI to explore and reuse all radar API endpoints
Model scores 2 models tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
Clef
Cloudflare
|
33.3%
|
— | Report | Verified |
| 2 |
Clef-Flash
Cloudflare
|
25.9%
|
— | Report | Verified |