Wikibench

Seal-0

reasoning

Multilingual: no

Seal-0 is a benchmark for evaluating agentic search capabilities, testing models' ability to navigate and retrieve information using tools.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: reasoning, search. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 6 of 6 results

  1. Kimi K2.5 self-reported llm-stats
    57.4%
  2. Kimi K2-Thinking-0905 self-reported llm-stats
    56.3%
  3. Qwen3.5-27B self-reported llm-stats
    47.2%
  4. Qwen3.5-397B-A17B self-reported llm-stats
    46.9%
  5. Qwen3.5-122B-A10B self-reported llm-stats
    44.1%
  6. Qwen3.5-35B-A3B self-reported llm-stats
    41.4%