New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
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.