eval-harness

metric

reasoning_tokens

better
neutral: a description
kind
descriptive: says what the output was, never whether it was good
decides
no goal
weighed by
no goal
recorded on
ag_news_200, cnn_dailymail_200, dbpedia_280, few_nerd_280, scifact_200, summeval_100

01what it measures, and how

Tokens a reasoning model spent thinking before it answered, as the provider reported them: a description of the call, not a quality.

Read from the provider's usage (completion_tokens_details.reasoning_tokens or its equivalent). Empty when the provider does not report it, never 0. Billed with the completion tokens, so cost_usd already includes it.

02on ag_news_200

gold/ag_news_200ag_anthropic_l_n200_v1: 0ag_anthropic_m_n200_v1: 0ag_anthropic_s_n200_v1: 0ag_deepseek_l_n200_v1: 0ag_deepseek_m_n200_v1: 0ag_deepseek_s_n200_v1: 0ag_gemma_l_n200_v1: 0ag_gemma_m_n200_v1: 0ag_gemma_s_n200_v1: 0ag_glm_l_n200_v1: 0ag_glm_m_n200_v1: 0ag_glm_s_n200_v1: 0ag_llama_l_n200_v1: 0ag_llama_m_n200_v1: 0ag_llama_s_n200_v1: 0ag_mistral_l_n200_v1: 0ag_mistral_m_n200_v1: 0ag_mistral_s_n200_v1: 0ag_openai_l_n200_v1: 0ag_openai_m_n200_v1: 0ag_openai_s_n200_v1: 0ag_qwen_l_n200_v1: 0ag_qwen_m_n200_v1: 0ag_qwen_s_n200_v1: 0gold/ag_news_200_adj1ag_anthropic_l_n200_v1 · adjudicated: 0ag_anthropic_m_n200_v1 · adjudicated: 0ag_anthropic_s_n200_v1 · adjudicated: 0ag_deepseek_l_n200_v1 · adjudicated: 0ag_deepseek_m_n200_v1 · adjudicated: 0ag_deepseek_s_n200_v1 · adjudicated: 0ag_gemma_l_n200_v1 · adjudicated: 0ag_gemma_m_n200_v1 · adjudicated: 0ag_gemma_s_n200_v1 · adjudicated: 0ag_glm_l_n200_v1 · adjudicated: 0ag_glm_m_n200_v1 · adjudicated: 0ag_glm_s_n200_v1 · adjudicated: 0ag_llama_l_n200_v1 · adjudicated: 0ag_llama_m_n200_v1 · adjudicated: 0ag_llama_s_n200_v1 · adjudicated: 0ag_mistral_l_n200_v1 · adjudicated: 0ag_mistral_m_n200_v1 · adjudicated: 0ag_mistral_s_n200_v1 · adjudicated: 0ag_openai_l_n200_v1 · adjudicated: 0ag_openai_m_n200_v1 · adjudicated: 0ag_openai_s_n200_v1 · adjudicated: 0ag_qwen_l_n200_v1 · adjudicated: 0ag_qwen_m_n200_v1 · adjudicated: 0ag_qwen_s_n200_v1 · adjudicated: 0-0.5better · 0.5

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 reasoning_tokensitemsscored against
ag_anthropic_l_n200_v10.000200gold/ag_news_200 gold
ag_anthropic_m_n200_v10.000200gold/ag_news_200 gold
ag_anthropic_s_n200_v10.000200gold/ag_news_200 gold
ag_deepseek_l_n200_v10.000200gold/ag_news_200 gold
ag_deepseek_m_n200_v10.000200gold/ag_news_200 gold
ag_deepseek_s_n200_v10.000200gold/ag_news_200 gold
ag_gemma_l_n200_v10.000200gold/ag_news_200 gold
ag_gemma_m_n200_v10.000200gold/ag_news_200 gold
ag_gemma_s_n200_v10.000200gold/ag_news_200 gold
ag_glm_l_n200_v10.000200gold/ag_news_200 gold
ag_glm_m_n200_v10.000200gold/ag_news_200 gold
ag_glm_s_n200_v10.000200gold/ag_news_200 gold
ag_llama_l_n200_v10.000200gold/ag_news_200 gold
ag_llama_m_n200_v10.000200gold/ag_news_200 gold
ag_llama_s_n200_v10.000200gold/ag_news_200 gold
ag_mistral_l_n200_v10.000200gold/ag_news_200 gold
ag_mistral_m_n200_v10.000200gold/ag_news_200 gold
ag_mistral_s_n200_v10.000200gold/ag_news_200 gold
ag_openai_l_n200_v10.000200gold/ag_news_200 gold
ag_openai_m_n200_v10.000200gold/ag_news_200 gold
ag_openai_s_n200_v10.000200gold/ag_news_200 gold
ag_qwen_l_n200_v10.000200gold/ag_news_200 gold
ag_qwen_m_n200_v10.000200gold/ag_news_200 gold
ag_qwen_s_n200_v10.000200gold/ag_news_200 gold
ag_anthropic_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_anthropic_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_anthropic_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_deepseek_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_deepseek_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_deepseek_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_gemma_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_gemma_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_gemma_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_glm_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_glm_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_glm_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_llama_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_llama_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_llama_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_mistral_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_mistral_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_mistral_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_openai_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_openai_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_openai_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_qwen_l_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_qwen_m_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold
ag_qwen_s_n200_v1 · adjudicated0.000200gold/ag_news_200_adj1 gold

03on cnn_dailymail_200

gold/cnn_dailymail_200cnn_anthropic_l_n200_v1: 0cnn_anthropic_m_n200_v1: 0cnn_anthropic_s_n200_v1: 0cnn_deepseek_l_n200_v1: 0cnn_deepseek_m_n200_v1: 0cnn_deepseek_s_n200_v1: 0cnn_gemma_l_n200_v1: 0cnn_gemma_m_n200_v1: 0cnn_gemma_s_n200_v1: 0cnn_glm_l_n200_v1: 0cnn_glm_m_n200_v1: 0cnn_glm_s_n200_v1: 0cnn_llama_l_n200_v1: 0cnn_llama_m_n200_v1: 0cnn_llama_s_n200_v1: 0cnn_mistral_l_n200_v1: 0cnn_mistral_m_n200_v1: 0cnn_mistral_s_n200_v1: 0cnn_openai_l_n200_v1: 0cnn_openai_m_n200_v1: 0cnn_openai_s_n200_v1: 0cnn_qwen_l_n200_v1: 0cnn_qwen_m_n200_v1: 0cnn_qwen_s_n200_v1: 0silver/cnn_dailymail_200cnn_anthropic_m_n200_v1 · silver: 0cnn_anthropic_s_n200_v1 · silver: 0cnn_deepseek_l_n200_v1 · silver: 0cnn_deepseek_m_n200_v1 · silver: 0cnn_deepseek_s_n200_v1 · silver: 0cnn_gemma_l_n200_v1 · silver: 0cnn_gemma_m_n200_v1 · silver: 0cnn_gemma_s_n200_v1 · silver: 0cnn_glm_l_n200_v1 · silver: 0cnn_glm_m_n200_v1 · silver: 0cnn_glm_s_n200_v1 · silver: 0cnn_llama_l_n200_v1 · silver: 0cnn_llama_m_n200_v1 · silver: 0cnn_llama_s_n200_v1 · silver: 0cnn_mistral_l_n200_v1 · silver: 0cnn_mistral_m_n200_v1 · silver: 0cnn_mistral_s_n200_v1 · silver: 0cnn_openai_l_n200_v1 · silver: 0cnn_openai_m_n200_v1 · silver: 0cnn_openai_s_n200_v1 · silver: 0cnn_qwen_l_n200_v1 · silver: 0cnn_qwen_m_n200_v1 · silver: 0cnn_qwen_s_n200_v1 · silver: 0judge judge-summ-pick-v1cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_deepseek_m_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_m_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_llama_l_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_l_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_openai_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_openai_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_openai_s_n200_v1 · judged/judge-summ-pick-v1: 0cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v1: 0cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v1: 0cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v1: 0judge judge-summ-pointwise-v1cnn_deepseek_m_n200_v1 · judged/judge-summ-pointwise-v1: 0judge judge-summ-v1cnn_anthropic_l_n200_v1 · judged/judge-summ-v1: 0cnn_anthropic_m_n200_v1 · judged/judge-summ-v1: 0cnn_anthropic_s_n200_v1 · judged/judge-summ-v1: 0cnn_deepseek_l_n200_v1 · judged/judge-summ-v1: 0cnn_deepseek_m_n200_v1 · judged/judge-summ-v1: 0cnn_deepseek_s_n200_v1 · judged/judge-summ-v1: 0cnn_gemma_l_n200_v1 · judged/judge-summ-v1: 0cnn_gemma_m_n200_v1 · judged/judge-summ-v1: 0cnn_gemma_s_n200_v1 · judged/judge-summ-v1: 0cnn_glm_l_n200_v1 · judged/judge-summ-v1: 0cnn_glm_m_n200_v1 · judged/judge-summ-v1: 0cnn_glm_s_n200_v1 · judged/judge-summ-v1: 0cnn_llama_l_n200_v1 · judged/judge-summ-v1: 0cnn_llama_m_n200_v1 · judged/judge-summ-v1: 0cnn_llama_s_n200_v1 · judged/judge-summ-v1: 0cnn_mistral_l_n200_v1 · judged/judge-summ-v1: 0cnn_mistral_m_n200_v1 · judged/judge-summ-v1: 0cnn_mistral_s_n200_v1 · judged/judge-summ-v1: 0cnn_openai_l_n200_v1 · judged/judge-summ-v1: 0cnn_openai_m_n200_v1 · judged/judge-summ-v1: 0cnn_openai_s_n200_v1 · judged/judge-summ-v1: 0cnn_qwen_l_n200_v1 · judged/judge-summ-v1: 0cnn_qwen_m_n200_v1 · judged/judge-summ-v1: 0cnn_qwen_s_n200_v1 · judged/judge-summ-v1: 0judge judge-summ-v2cnn_anthropic_l_n200_v1 · judged/judge-summ-v2: 0cnn_anthropic_m_n200_v1 · judged/judge-summ-v2: 0cnn_anthropic_s_n200_v1 · judged/judge-summ-v2: 0cnn_deepseek_l_n200_v1 · judged/judge-summ-v2: 0cnn_deepseek_m_n200_v1 · judged/judge-summ-v2: 0cnn_deepseek_s_n200_v1 · judged/judge-summ-v2: 0cnn_gemma_l_n200_v1 · judged/judge-summ-v2: 0cnn_gemma_m_n200_v1 · judged/judge-summ-v2: 0cnn_gemma_s_n200_v1 · judged/judge-summ-v2: 0cnn_glm_l_n200_v1 · judged/judge-summ-v2: 0cnn_glm_m_n200_v1 · judged/judge-summ-v2: 0cnn_glm_s_n200_v1 · judged/judge-summ-v2: 0cnn_llama_l_n200_v1 · judged/judge-summ-v2: 0cnn_llama_m_n200_v1 · judged/judge-summ-v2: 0cnn_llama_s_n200_v1 · judged/judge-summ-v2: 0cnn_mistral_l_n200_v1 · judged/judge-summ-v2: 0cnn_mistral_m_n200_v1 · judged/judge-summ-v2: 0cnn_mistral_s_n200_v1 · judged/judge-summ-v2: 0cnn_openai_l_n200_v1 · judged/judge-summ-v2: 0cnn_openai_m_n200_v1 · judged/judge-summ-v2: 0cnn_openai_s_n200_v1 · judged/judge-summ-v2: 0cnn_qwen_l_n200_v1 · judged/judge-summ-v2: 0cnn_qwen_m_n200_v1 · judged/judge-summ-v2: 0cnn_qwen_s_n200_v1 · judged/judge-summ-v2: 0-0.5better · 0.5

Not drawn: cnn_anthropic_l_n200_v1 · silver, scored against the reference it wrote (its row is in the table).

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 reasoning_tokensitemsscored against
cnn_anthropic_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_anthropic_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_anthropic_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_deepseek_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_deepseek_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_deepseek_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_gemma_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_gemma_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_gemma_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_glm_l_n200_v10.000199gold/cnn_dailymail_200 gold
cnn_glm_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_glm_s_n200_v10.000199gold/cnn_dailymail_200 gold
cnn_llama_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_llama_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_llama_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_mistral_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_mistral_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_mistral_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_openai_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_openai_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_openai_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_qwen_l_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_qwen_m_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_qwen_s_n200_v10.000200gold/cnn_dailymail_200 gold
cnn_anthropic_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_anthropic_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_anthropic_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_deepseek_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_deepseek_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_deepseek_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_gemma_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_gemma_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_gemma_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_glm_l_n200_v1 · silver0.000199silver/cnn_dailymail_200 silver
cnn_glm_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_glm_s_n200_v1 · silver0.000199silver/cnn_dailymail_200 silver
cnn_llama_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_llama_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_llama_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_mistral_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_mistral_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_mistral_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_openai_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_openai_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_openai_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_qwen_l_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_qwen_m_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_qwen_s_n200_v1 · silver0.000200silver/cnn_dailymail_200 silver
cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_deepseek_m_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_m_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-v10.000197judge 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-v10.000197judge judge-summ-pick-v1
cnn_llama_l_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_l_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_openai_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_openai_m_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_openai_s_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v10.000198judge judge-summ-pick-v1
cnn_qwen_m_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
cnn_deepseek_m_n200_v1 · judged/judge-summ-pointwise-v10.000200judge judge-summ-pointwise-v1
cnn_anthropic_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_anthropic_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_anthropic_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_deepseek_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_deepseek_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_deepseek_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_gemma_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_gemma_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_gemma_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_glm_l_n200_v1 · judged/judge-summ-v10.000196judge judge-summ-v1
cnn_glm_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_glm_s_n200_v1 · judged/judge-summ-v10.000196judge judge-summ-v1
cnn_llama_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_llama_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_llama_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_mistral_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_mistral_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_mistral_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_openai_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_openai_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_openai_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_qwen_l_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_qwen_m_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_qwen_s_n200_v1 · judged/judge-summ-v10.000197judge judge-summ-v1
cnn_anthropic_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_anthropic_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_anthropic_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_deepseek_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_deepseek_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_deepseek_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_gemma_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_gemma_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_gemma_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_glm_l_n200_v1 · judged/judge-summ-v20.000199judge judge-summ-v2
cnn_glm_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_glm_s_n200_v1 · judged/judge-summ-v20.000199judge judge-summ-v2
cnn_llama_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_llama_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_llama_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_mistral_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_mistral_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_mistral_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_openai_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_openai_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_openai_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_qwen_l_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_qwen_m_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2
cnn_qwen_s_n200_v1 · judged/judge-summ-v20.000200judge judge-summ-v2

04on dbpedia_280

gold/dbpedia_280db_anthropic_l_n200_v1: 0db_anthropic_m_n200_v1: 0db_anthropic_s_n200_v1: 0db_deepseek_l_n200_v1: 0db_deepseek_m_n200_v1: 0db_deepseek_s_n200_v1: 0db_gemma_l_n200_v1: 0db_gemma_m_n200_v1: 0db_gemma_s_n200_v1: 0db_glm_l_n200_v1: 0db_glm_m_n200_v1: 0db_glm_s_n200_v1: 0db_llama_l_n200_v1: 0db_llama_m_n200_v1: 0db_llama_s_n200_v1: 0db_mistral_l_n200_v1: 0db_mistral_m_n200_v1: 0db_mistral_s_n200_v1: 0db_openai_l_n200_v1: 0db_openai_m_n200_v1: 0db_openai_s_n200_v1: 0db_qwen_l_n200_v1: 0db_qwen_m_n200_v1: 0db_qwen_s_n200_v1: 0-0.5better · 0.5

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

05on few_nerd_280

gold/few_nerd_280fn_anthropic_l_n200_v1: 0fn_anthropic_m_n200_v1: 0fn_anthropic_s_n200_v1: 0fn_deepseek_l_n200_v1: 0fn_deepseek_m_n200_v1: 0fn_deepseek_s_n200_v1: 0fn_gemma_l_n200_v1: 0fn_gemma_m_n200_v1: 0fn_gemma_s_n200_v1: 0fn_glm_l_n200_v1: 0fn_glm_m_n200_v1: 0fn_glm_s_n200_v1: 0fn_llama_l_n200_v1: 0fn_llama_m_n200_v1: 0fn_llama_s_n200_v1: 0fn_mistral_l_n200_v1: 0fn_mistral_m_n200_v1: 0fn_mistral_s_n200_v1: 0fn_openai_l_n200_v1: 0fn_openai_m_n200_v1: 0fn_openai_s_n200_v1: 0fn_qwen_l_n200_v1: 0fn_qwen_m_n200_v1: 0fn_qwen_s_n200_v1: 0-0.5better · 0.5

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

06on scifact_200

gold/scifact_200sf_deepseek_m_n200_v1: 3.5sf_deepseek_s_n200_v1: 0sf_gemma_l_n200_v1: 0sf_gemma_m_n200_v1: 0sf_gemma_s_n200_v1: 0sf_glm_m_n200_v1: 0sf_glm_s_n200_v1: 0sf_llama_l_n200_v1: 0sf_llama_m_n200_v1: 0sf_llama_s_n200_v1: 0sf_mistral_s_n200_v1: 0sf_qwen_s_n200_v1: 0sf_glm_s_bm25first_n200_v1 · pair: 0sf_glm_s_e5first_n200_v1 · pair: 0sf_qwen_s_bm25first_n200_v1 · pair: 0sf_qwen_s_e5first_n200_v1 · pair: 0sf_llama_l_n200_v1 · repeats: 0sf_llama_s_n200_v1 · repeats: 0sf_qwen_s_n200_v1 · repeats: 00better · 3.5

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

07on summeval_100

gold/summeval_100se_anthropic_l_n100_v1: 0se_anthropic_m_n100_v1: 0se_anthropic_s_n100_v1: 0se_deepseek_l_n100_v1: 0se_deepseek_m_n100_v1: 0se_deepseek_s_n100_v1: 0se_gemma_l_n100_pairwise_v1: 0se_gemma_l_n100_pick_v1: 0se_gemma_l_n100_v1: 0se_gemma_m_n100_v1: 0se_gemma_s_n100_v1: 0se_glm_l_n100_v1: 0se_glm_m_n100_v1: 0se_glm_s_n100_v1: 0se_llama_l_n100_v1: 0se_llama_m_n100_v1: 0se_llama_s_n100_v1: 0se_mistral_l_n100_v1: 0se_mistral_m_n100_v1: 0se_mistral_s_n100_v1: 0se_openai_l_n100_v1: 0se_openai_m_n100_v1: 0se_openai_s_n100_v1: 0se_qwen37max_n100_v1: 0se_qwen_m_n100_v1: 0se_qwen_s_n100_pairwise_v1: 0se_qwen_s_n100_pick_v1: 0se_qwen_s_n100_v1: 0se_gemma_l_pubtext_n100_v1 · pair: 0se_gemma_l_pubtextcw_n100_v1 · pair: 0-0.5better · 0.5

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 reasoning_tokensitemsscored against
se_anthropic_l_n100_v10.000100gold/summeval_100 gold
se_anthropic_m_n100_v10.000100gold/summeval_100 gold
se_anthropic_s_n100_v10.000100gold/summeval_100 gold
se_deepseek_l_n100_v10.000100gold/summeval_100 gold
se_deepseek_m_n100_v10.000100gold/summeval_100 gold
se_deepseek_s_n100_v10.000100gold/summeval_100 gold
se_gemma_l_n100_pairwise_v10.000100gold/summeval_100 gold
se_gemma_l_n100_pick_v10.000100gold/summeval_100 gold
se_gemma_l_n100_v10.000100gold/summeval_100 gold
se_gemma_m_n100_v10.000100gold/summeval_100 gold
se_gemma_s_n100_v10.000100gold/summeval_100 gold
se_glm_l_n100_v10.000100gold/summeval_100 gold
se_glm_m_n100_v10.000100gold/summeval_100 gold
se_glm_s_n100_v10.000100gold/summeval_100 gold
se_llama_l_n100_v10.000100gold/summeval_100 gold
se_llama_m_n100_v10.000100gold/summeval_100 gold
se_llama_s_n100_v10.000100gold/summeval_100 gold
se_mistral_l_n100_v10.000100gold/summeval_100 gold
se_mistral_m_n100_v10.000100gold/summeval_100 gold
se_mistral_s_n100_v10.000100gold/summeval_100 gold
se_openai_l_n100_v10.000100gold/summeval_100 gold
se_openai_m_n100_v10.000100gold/summeval_100 gold
se_openai_s_n100_v10.000100gold/summeval_100 gold
se_qwen37max_n100_v10.000100gold/summeval_100 gold
se_qwen_m_n100_v10.000100gold/summeval_100 gold
se_qwen_s_n100_pairwise_v10.000100gold/summeval_100 gold
se_qwen_s_n100_pick_v10.000100gold/summeval_100 gold
se_qwen_s_n100_v10.000100gold/summeval_100 gold
se_gemma_l_pubtext_n100_v1 · pair0.000100gold/summeval_100 gold
se_gemma_l_pubtextcw_n100_v1 · pair0.000100gold/summeval_100 gold