The AI arena is free today

Open Superagent

KORABench

Implementation

Progress Over Time

Interactive timeline showing model performance evolution on KORABench

State-of-the-art frontier
Open
Proprietary

KORABench Leaderboard

1 models
ContextCostLicense
1
Mistral AI
Mistral AI
1.1T1.0M$0.70 / $2.10
Notice missing or incorrect data?
About this benchmark

What is KORABench?

KORABench is a nonprofit, independent, open-source benchmark for child-safety behavior in AI systems, measuring model behavior against 26 child-specific risks.

KORABench is a text benchmark evaluating models on safety tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–2 scale. The current average is 1.7, with the leader at 1.7.

Compare leaders on the best AI for safety leaderboards.

Current leaders

Mistral Large 4 from Mistral AI currently leads the KORABench leaderboard with a score of 1.691 across 1 evaluated AI models.

1Mistral Large 4Mistral AI1.691

FAQ

Common questions about the KORABench benchmark and leaderboard.

What is the KORABench benchmark?

KORABench is a nonprofit, independent, open-source benchmark for child-safety behavior in AI systems, measuring model behavior against 26 child-specific risks.

What is the KORABench leaderboard?

The KORABench leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Mistral Large 4 by Mistral AI leads with a score of 1.691. The average score across all models is 1.691.

What is the highest KORABench score?

The highest KORABench score is 1.691, achieved by Mistral Large 4 from Mistral AI.

How many models are evaluated on KORABench?

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

Where can I find the KORABench dataset?

The KORABench dataset is available at https://korabench.ai/.

What categories does KORABench cover?

KORABench is categorized under safety. The benchmark evaluates text models.

Which model offers the best value on KORABench?

Among models scoring within 10% of the leader, Mistral Large 4 from Mistral AI is the cheapest, at $0.70 per million input tokens with a score of 1.691.

How recent are the KORABench leaderboard results?

The KORABench leaderboard was last updated in November 2026 and currently includes 1 evaluated models.