reasoning benchmark
Seal-0
Seal-0 is a benchmark for evaluating agentic search capabilities, testing models' ability to navigate and retrieve information using tools.
Updated Aug 7, 2026
Published models6
Registry coverage6
MetricScore
EvidenceB
Seal-0 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 57.4% | 100.0% | 6 | C | |
| 2 | MA | 56.3% | 80.0% | 6 | C | |
| 3 | AC | 47.2% | 60.0% | 6 | C | |
| 4 | AC | 46.9% | 40.0% | 6 | C | |
| 5 | AC | 44.1% | 20.0% | 6 | C | |
| 6 | AC | 41.4% | 0.0% | 6 | C |
Score distribution
Top published rows on the benchmark's original scale.
Seal-0 highlights
The top published results on this benchmark's own scale.
What is Seal-0?
Definition and scoring fields from the benchmark registry.
Seal-0 is a benchmark for evaluating agentic search capabilities, testing models' ability to navigate and retrieve information using tools.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Seal-0
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- seal-0|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Seal-0.
Which model scores highest on Seal-0?
Kimi K2.5 is currently ranked first with 57.4%.
What does Seal-0 measure?
Seal-0 is a benchmark for evaluating agentic search capabilities, testing models' ability to navigate and retrieve information using tools.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
6 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.