reference

`gold/dbpedia_280` gold

Promoted as gold: the yardstick a decision rests on.
Promoted from person the dataset's authors, 2026-09-27: promoted before labels existed (0.6.0): its tier was given when it was made

01what it is

tier: gold
dataset: dbpedia_280
promoted from: person the dataset's authors
why: promoted before labels existed (0.6.0): its tier was given when it was made
items: 280
created: 2026-09-27T11:58:24Z

02scored against it · 29

scored against silverscored by a judgewrote the reference it is scored againstscored against a label set, not a reference setunmarked rows are scored against gold

arm	metric	mean	items
db_qwen_m_n200_v1	correct	0.993	280	inspect
db_anthropic_l_n200_v1	correct	0.989	280	inspect
db_bert_base_fy_n200_v1	correct	0.986	280	inspect
db_deepseek_l_n200_v1	correct	0.986	280	inspect
db_gemma_m_n200_v1	correct	0.986	280	inspect
db_glm_m_n200_v1	correct	0.986	280	inspect
db_qwen_s_n200_v1	correct	0.986	280	inspect
db_bert_base_fy_n200_v1 · linux	correct	0.986	280	inspect
db_anthropic_m_n200_v1	correct	0.982	280	inspect
db_openai_m_n200_v1	correct	0.982	280	inspect
db_anthropic_s_n200_v1	correct	0.979	280	inspect
db_llama_m_n200_v1	correct	0.979	280	inspect
db_deepseek_m_n200_v1	correct	0.975	280	inspect
db_gemma_l_n200_v1	correct	0.975	280	inspect
db_gemma_s_n200_v1	correct	0.975	280	inspect
db_llama_l_n200_v1	correct	0.975	280	inspect
db_openai_l_n200_v1	correct	0.975	280	inspect
db_openai_s_n200_v1	correct	0.975	280	inspect
db_glm_l_n200_v1	correct	0.968	280	inspect
db_qwen_l_n200_v1	correct	0.968	280	inspect
db_mistral_l_n200_v1	correct	0.964	280	inspect
db_llama_s_n200_v1	correct	0.957	280	inspect
db_mistral_m_n200_v1	correct	0.957	280	inspect
db_mistral_s_n200_v1	correct	0.957	280	inspect
db_deepseek_s_n200_v1	correct	0.943	280	inspect
db_glm_s_n200_v1	correct	0.939	280	inspect
db_keyword_n200_v1	correct	0.707	280	inspect
db_bart_mnli_n200_v1	correct	0.629	280	inspect
db_constant_n200_v1	correct	0.071	280	inspect

gold/dbpedia_280 gold

`gold/dbpedia_280` gold