Wikibench

AA-LCR

reasoning

Multilingual: no

Agent Arena Long Context Reasoning benchmark

Methodology

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

Leaderboard

Showing 8 of 8 results

  1. Kimi K2.5 self-reported llm-stats
    70.0%
  2. Qwen3.5-397B-A17B self-reported llm-stats
    68.7%
  3. Qwen3.6 Plus self-reported llm-stats
    68.3%
  4. Qwen3.5-122B-A10B self-reported llm-stats
    66.9%
  5. Qwen3.5-27B self-reported llm-stats
    66.1%
  6. MiniMax M2.1 self-reported llm-stats
    62.0%
  7. Qwen3.5-35B-A3B self-reported llm-stats
    58.5%
  8. Nemotron 3 Super (120B A12B) self-reported llm-stats
    58.3%