AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

Creative Writing v3

EQ-Bench Creative Writing v3 is an LLM-judged creative writing benchmark that evaluates models across 32 writing prompts with 3 iterations per prompt. Uses a hybrid scoring system combining rubric assessment and Elo ratings through pairwise comparisons. Challenges models in areas like humor, romance, spatial awareness, and unique perspectives to assess emotional intelligence and creative writing capabilities.

评测信息与证据

来源
LLM Stats
发布者
未收录
评测发布日期
未收录
采集日期
2026-08-17
模态
text

本站保留来源报告的结果,不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期;不同运行条件不能直接合并为统一排名。

原始资料

报告成绩 13

按来源中的观察顺序展示,顺序不代表排名。日期保留原始精度。

模型数值单位协议报告日期与口径来源
Qwen3-235B-A22B-Instruct-25070.875未收录未收录2025-07-22 · model_announcementLLM Stats
Qwen3 VL 235B A22B Instruct0.865未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3-235B-A22B-Thinking-25070.861未收录未收录2025-07-25 · model_announcementLLM Stats
Grok-4.1 Thinking0.86095未收录未收录2025-11-17 · model_announcementLLM Stats
Qwen3 VL 235B A22B Thinking0.857未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3 VL 32B Instruct0.856未收录未收录2025-09-22 · model_announcementLLM Stats
Grok-4.10.8543未收录未收录2025-11-17 · model_announcementLLM Stats
Qwen3-Next-80B-A3B-Instruct0.853未收录未收录2025-09-10 · model_announcementLLM Stats
Qwen3 VL 30B A3B Instruct0.846未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3 VL 32B Thinking0.833未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3 VL 30B A3B Thinking0.825未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3 VL 8B Thinking0.824未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3 VL 4B Thinking0.761未收录未收录2025-09-22 · model_announcementLLM Stats