Decision Benchmark

DecisionBench (Hanno Labs)

DecisionBench v1 by Hanno Labs, a decision-making benchmark suite (https://huggingface.co/datasets/Hanno-Labs/decision-bench). Values reported as percentage.

Category

Decision

Score type

percent

Scale

100%

higher is better

Models tested

1

What is DecisionBench (Hanno Labs)?

DecisionBench (Hanno Labs) is a benchmark for the abilities the benchmark was built to measure. The official description says: "DecisionBench v1 by Hanno Labs, a decision-making benchmark suite (https://huggingface.co/datasets/Hanno-Labs/decision-bench)". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

DecisionBench (Hanno Labs) measures the abilities the benchmark was built to measure. In detail, it checks:

  • tasks representative of the benchmark's stated purpose
  • consistent scoring rules so models can be compared fairly
  • difficulty calibrated so top models do not max out easily

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: DecisionBench v1 by Hanno Labs, a decision-making benchmark suite (https://huggingface.co/datasets/Hanno-Labs/decision-bench). Values reported as percentage.

Frequently asked questions

What is the DecisionBench (Hanno Labs) benchmark?

DecisionBench (Hanno Labs) is a benchmark for the abilities the benchmark was built to measure. The official description says: 'DecisionBench v1 by Hanno Labs, a decision-making benchmark suite (https://huggingface.co/datasets/Hanno-Labs/decision-bench)'. Below we describe in simple words what benchmarks of this type generally examine.

What does DecisionBench (Hanno Labs) test?

DecisionBench (Hanno Labs) mainly measures the abilities the benchmark was built to measure. Concretely, it checks: tasks representative of the benchmark's stated purpose; consistent scoring rules so models can be compared fairly; difficulty calibrated so top models do not max out easily.

How is the DecisionBench (Hanno Labs) 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 DecisionBench (Hanno Labs) data and scores?

The official source is https://huggingface.co/datasets/Hanno-Labs/decision-bench. 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/decisionbench-hanno-labs/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 1 model tested

Reset
# Model Score Date Source Verified
1 d1-2B
LiquidAI
77.1%
— LiquidAI/d1-2B model card (performance table) Unverified