eval-harness

metric

judge_qwen_s

better
higher
kind
quality: measured against a reference or by a judge
decides
no goal
weighed by
no goal
recorded on
cnn_dailymail_200

01what it measures, and how

Judge qwen_s's mean score for the output, on the scorer's scale.

A project explains its own metric at length with METRIC_DESCRIPTIONS = {"judge_qwen_s": {"summary": "…", "details": "…"}}.

02on cnn_dailymail_200

judge judge-summ-v1cnn_anthropic_l_n200_v1 · judged/judge-summ-v1: 4.957cnn_anthropic_m_n200_v1 · judged/judge-summ-v1: 4.94cnn_anthropic_s_n200_v1 · judged/judge-summ-v1: 4.928cnn_deepseek_m_n200_v1 · judged/judge-summ-v1: 4.879cnn_qwen_m_n200_v1 · judged/judge-summ-v1: 4.83cnn_deepseek_l_n200_v1 · judged/judge-summ-v1: 4.817cnn_glm_m_n200_v1 · judged/judge-summ-v1: 4.786cnn_qwen_l_n200_v1 · judged/judge-summ-v1: 4.773cnn_openai_s_n200_v1 · judged/judge-summ-v1: 4.753cnn_deepseek_s_n200_v1 · judged/judge-summ-v1: 4.73cnn_openai_m_n200_v1 · judged/judge-summ-v1: 4.713cnn_gemma_s_n200_v1 · judged/judge-summ-v1: 4.702cnn_mistral_s_n200_v1 · judged/judge-summ-v1: 4.694cnn_openai_l_n200_v1 · judged/judge-summ-v1: 4.678cnn_gemma_m_n200_v1 · judged/judge-summ-v1: 4.586cnn_llama_s_n200_v1 · judged/judge-summ-v1: 4.576cnn_mistral_m_n200_v1 · judged/judge-summ-v1: 4.576cnn_gemma_l_n200_v1 · judged/judge-summ-v1: 4.575cnn_llama_l_n200_v1 · judged/judge-summ-v1: 4.56cnn_glm_l_n200_v1 · judged/judge-summ-v1: 4.537cnn_llama_m_n200_v1 · judged/judge-summ-v1: 4.519cnn_mistral_l_n200_v1 · judged/judge-summ-v1: 4.509cnn_qwen_s_n200_v1 · judged/judge-summ-v1: 4.489cnn_glm_s_n200_v1 · judged/judge-summ-v1: 4.338cnn_bart_l_n200_v1 · judged/judge-summ-v1: 3.607cnn_bart_m_n200_v1 · judged/judge-summ-v1: 3.171cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v1: 3.145cnn_lead3_n200_v1 · judged/judge-summ-v1: 3.122cnn_bart_s_n200_v1 · judged/judge-summ-v1: 2.829judge judge-summ-pick-v1cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v1: 0.419cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1: 0.212cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v1: 0.141cnn_deepseek_m_n200_v1 · judged/judge-summ-pick-v1: 0.076cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v1: 0.071cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v1: 0.025cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v1: 0.02cnn_openai_s_n200_v1 · judged/judge-summ-pick-v1: 0.01cnn_gemma_m_n200_v1 · judged/judge-summ-pick-v1: 0.0051cnn_llama_l_n200_v1 · judged/judge-summ-pick-v1: 0.0051cnn_mistral_l_n200_v1 · judged/judge-summ-pick-v1: 0.0051cnn_openai_l_n200_v1 · judged/judge-summ-pick-v1: 0.0051cnn_openai_m_n200_v1 · judged/judge-summ-pick-v1: 0.0051cnn_bart_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_bart_l_xsum_n200_v1 · judged/judge-summ-pick-v1: 0cnn_bart_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_bart_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_deepseek_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_gemma_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_glm_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_glm_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_glm_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_lead3_n200_v1 · judged/judge-summ-pick-v1: 0cnn_llama_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_llama_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_mistral_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_mistral_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v1: 00better · 4.957

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

armmean judge_qwen_sitemsscored against
cnn_anthropic_l_n200_v1 · judged/judge-summ-v14.957197judge judge-summ-v1
cnn_anthropic_m_n200_v1 · judged/judge-summ-v14.940197judge judge-summ-v1
cnn_anthropic_s_n200_v1 · judged/judge-summ-v14.928197judge judge-summ-v1
cnn_deepseek_m_n200_v1 · judged/judge-summ-v14.879197judge judge-summ-v1
cnn_qwen_m_n200_v1 · judged/judge-summ-v14.830197judge judge-summ-v1
cnn_deepseek_l_n200_v1 · judged/judge-summ-v14.817197judge judge-summ-v1
cnn_glm_m_n200_v1 · judged/judge-summ-v14.786197judge judge-summ-v1
cnn_qwen_l_n200_v1 · judged/judge-summ-v14.773197judge judge-summ-v1
cnn_openai_s_n200_v1 · judged/judge-summ-v14.753197judge judge-summ-v1
cnn_deepseek_s_n200_v1 · judged/judge-summ-v14.730197judge judge-summ-v1
cnn_openai_m_n200_v1 · judged/judge-summ-v14.713197judge judge-summ-v1
cnn_gemma_s_n200_v1 · judged/judge-summ-v14.702197judge judge-summ-v1
cnn_mistral_s_n200_v1 · judged/judge-summ-v14.694197judge judge-summ-v1
cnn_openai_l_n200_v1 · judged/judge-summ-v14.678197judge judge-summ-v1
cnn_gemma_m_n200_v1 · judged/judge-summ-v14.586197judge judge-summ-v1
cnn_llama_s_n200_v1 · judged/judge-summ-v14.576197judge judge-summ-v1
cnn_mistral_m_n200_v1 · judged/judge-summ-v14.576197judge judge-summ-v1
cnn_gemma_l_n200_v1 · judged/judge-summ-v14.575197judge judge-summ-v1
cnn_llama_l_n200_v1 · judged/judge-summ-v14.560197judge judge-summ-v1
cnn_glm_l_n200_v1 · judged/judge-summ-v14.537197judge judge-summ-v1
cnn_llama_m_n200_v1 · judged/judge-summ-v14.519197judge judge-summ-v1
cnn_mistral_l_n200_v1 · judged/judge-summ-v14.509197judge judge-summ-v1
cnn_qwen_s_n200_v1 · judged/judge-summ-v14.489197judge judge-summ-v1
cnn_glm_s_n200_v1 · judged/judge-summ-v14.338197judge judge-summ-v1
cnn_bart_l_n200_v1 · judged/judge-summ-v13.607197judge judge-summ-v1
cnn_bart_m_n200_v1 · judged/judge-summ-v13.171197judge judge-summ-v1
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v13.145197judge judge-summ-v1
cnn_lead3_n200_v1 · judged/judge-summ-v13.122197judge judge-summ-v1
cnn_bart_s_n200_v1 · judged/judge-summ-v12.829197judge judge-summ-v1
cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v10.419198judge judge-summ-pick-v1
cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v10.212198judge judge-summ-pick-v1
cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v10.141198judge judge-summ-pick-v1
cnn_deepseek_m_n200_v1 · judged/judge-summ-pick-v10.076198judge judge-summ-pick-v1
cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v10.071198judge judge-summ-pick-v1
cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v10.025198judge judge-summ-pick-v1
cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v10.020198judge judge-summ-pick-v1
cnn_openai_s_n200_v1 · judged/judge-summ-pick-v10.010198judge judge-summ-pick-v1
cnn_gemma_m_n200_v1 · judged/judge-summ-pick-v10.005198judge judge-summ-pick-v1
cnn_llama_l_n200_v1 · judged/judge-summ-pick-v10.005198judge judge-summ-pick-v1
cnn_mistral_l_n200_v1 · judged/judge-summ-pick-v10.005198judge judge-summ-pick-v1
cnn_openai_l_n200_v1 · judged/judge-summ-pick-v10.005198judge judge-summ-pick-v1
cnn_openai_m_n200_v1 · judged/judge-summ-pick-v10.005198judge judge-summ-pick-v1
cnn_bart_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_bart_m_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_bart_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_deepseek_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_gemma_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_glm_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_glm_m_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_glm_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_lead3_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_llama_m_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_llama_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_mistral_m_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_mistral_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1