// BENCHMARK

Seal-0 benchmark

AI model leaderboard for the Seal-0 benchmark. Compare how large language models score on Seal-0, see the full ranking, and understand what this AI benchmark measures. Kimi K2 Thinking currently leads with 56.3. Agentic web-browsing benchmark — sealed (private) hard subset for clean leaderboard tracking.

Leaderboard

# Model Organization Score Variant Source
#1 Kimi K2 Thinking Moonshot 56.3 thinking-w-tools official ↗
#2 Kimi K2 Moonshot 25.2 k2-0905-w-tools-cited-k2-thinking official ↗

Frequently asked questions about Seal-0

What is the Seal-0 benchmark?

Agentic web-browsing benchmark — sealed (private) hard subset for clean leaderboard tracking.

How is the Seal-0 benchmark scored?

Seal-0 is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on Seal-0?

As of the latest reported scores on GenAIList, Kimi K2 Thinking achieves the highest result on Seal-0 with a score of 56.3.

Is a higher Seal-0 score better?

Yes. On Seal-0 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.