reference

`gold/few_nerd_280` gold

Promoted as gold: the yardstick a decision rests on.
Promoted from person the dataset's authors, 2026-09-28: promoted before labels existed (0.6.0): its tier was given when it was made

01what it is

tier: gold
dataset: few_nerd_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: 2026-09-28T05:40:45Z

02scored against it · 28

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
fn_span_marker_n200_v1	f1	0.767	280	inspect
fn_openai_m_n200_v1	f1	0.686	280	inspect
fn_anthropic_l_n200_v1	f1	0.680	280	inspect
fn_gemma_m_n200_v1	f1	0.673	280	inspect
fn_openai_l_n200_v1	f1	0.672	280	inspect
fn_anthropic_m_n200_v1	f1	0.666	280	inspect
fn_qwen_s_n200_v1	f1	0.665	280	inspect
fn_qwen_m_n200_v1	f1	0.655	280	inspect
fn_gemma_l_n200_v1	f1	0.648	280	inspect
fn_qwen_l_n200_v1	f1	0.624	280	inspect
fn_deepseek_m_n200_v1	f1	0.615	280	inspect
fn_llama_l_n200_v1	f1	0.599	280	inspect
fn_mistral_l_n200_v1	f1	0.598	280	inspect
fn_openai_s_n200_v1	f1	0.595	280	inspect
fn_glm_m_n200_v1	f1	0.594	280	inspect
fn_mistral_m_n200_v1	f1	0.591	280	inspect
fn_deepseek_l_n200_v1	f1	0.587	280	inspect
fn_anthropic_s_n200_v1	f1	0.584	280	inspect
fn_deepseek_s_n200_v1	f1	0.576	280	inspect
fn_llama_m_n200_v1	f1	0.574	280	inspect
fn_llama_s_n200_v1	f1	0.569	280	inspect
fn_glm_l_n200_v1	f1	0.566	280	inspect
fn_glm_s_n200_v1	f1	0.553	280	inspect
fn_gemma_s_n200_v1	f1	0.550	280	inspect
fn_mistral_s_n200_v1	f1	0.524	280	inspect
fn_gliner_n200_v1	f1	0.454	280	inspect
fn_capitalized_n200_v1	f1	0.191	280	inspect
fn_nothing_n200_v1	f1	0.125	280	inspect

gold/few_nerd_280 gold

`gold/few_nerd_280` gold