Benchmark
Seal-0 Benchmark
What is Seal-0?
Seal-0 is a benchmark for evaluating agentic search capabilities, testing models' ability to navigate and retrieve information using tools.
- Modality
- text
- Evaluates
- reasoning, search
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 6
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/seal-0?top_n=500
Seal-0 results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Kimi K2-Thinking-0905 | Moonshot AI | 0.563 | 2025-09-05 | evidence |
| Kimi K2.5 | Moonshot AI | 0.574 | 2026-01-27 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.441 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.472 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.414 | 2026-02-24 | evidence |
| Qwen3.5-397B-A17B | Qwen | 0.469 | 2026-02-16 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.