The AI arena is free today

Open Superagent
All benchmarks

CBNSL

Paper

Progress Over Time

Interactive timeline showing model performance evolution on CBNSL

State-of-the-art frontier
Open
Proprietary

CBNSL Leaderboard

1 models
ContextCostLicense
1
Moonshot AI
Kimi K2 Instruct
Moonshot AI
1.0T——
Notice missing or incorrect data?
About this benchmark

What is CBNSL?

Curriculum Learning of Bayesian Network Structures (CBNSL) benchmark for evaluating algorithms that learn Bayesian network structures from data using curriculum learning techniques. The benchmark uses networks from the bnlearn repository and evaluates structure learning performance using BDeu scoring metrics.

CBNSL is a text benchmark evaluating models on math and reasoning tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 1.0, with the leader at 1.0.

Compare leaders on the best AI for math and best AI for reasoning leaderboards.

Current leaders

Kimi K2 Instruct from Moonshot AI currently leads the CBNSL leaderboard with a score of 0.956 across 1 evaluated AI models.

1Kimi K2 InstructMoonshot AI95.6%

FAQ

Common questions about the CBNSL benchmark and leaderboard.

What is the CBNSL benchmark?

Curriculum Learning of Bayesian Network Structures (CBNSL) benchmark for evaluating algorithms that learn Bayesian network structures from data using curriculum learning techniques. The benchmark uses networks from the bnlearn repository and evaluates structure learning performance using BDeu scoring metrics.

What is the CBNSL leaderboard?

The CBNSL leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Kimi K2 Instruct by Moonshot AI leads with a score of 0.956. The average score across all models is 0.956.

What is the highest CBNSL score?

The highest CBNSL score is 0.956, achieved by Kimi K2 Instruct from Moonshot AI.

How many models are evaluated on CBNSL?

1 models have been evaluated on the CBNSL benchmark, with 0 verified results and 1 self-reported results.

Where can I find the CBNSL paper?

The CBNSL paper is available at http://proceedings.mlr.press/v45/Zhao15a.pdf. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does CBNSL cover?

CBNSL is categorized under math and reasoning. The benchmark evaluates text models.

What is the best open-source model on CBNSL?

Kimi K2 Instruct by Moonshot AI is the top-ranked open-source model on CBNSL, with a score of 0.956 (rank #1).

How recent are the CBNSL leaderboard results?

The CBNSL leaderboard was last updated in August 2026 and currently includes 1 evaluated models.