| cnn_anthropic_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_anthropic_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_anthropic_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_deepseek_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_deepseek_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_deepseek_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_gemma_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_gemma_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_gemma_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_glm_l_n200_v1 | 0.000 | 199 | gold/cnn_dailymail_200 gold |
| cnn_glm_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_glm_s_n200_v1 | 0.000 | 199 | gold/cnn_dailymail_200 gold |
| cnn_llama_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_llama_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_llama_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_mistral_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_mistral_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_mistral_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_openai_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_openai_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_openai_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_qwen_l_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_qwen_m_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_qwen_s_n200_v1 | 0.000 | 200 | gold/cnn_dailymail_200 gold |
| cnn_anthropic_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_anthropic_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_anthropic_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_deepseek_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_deepseek_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_deepseek_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_gemma_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_gemma_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_gemma_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_glm_l_n200_v1 · silver | 0.000 | 199 | silver/cnn_dailymail_200 silver |
| cnn_glm_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_glm_s_n200_v1 · silver | 0.000 | 199 | silver/cnn_dailymail_200 silver |
| cnn_llama_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_llama_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_llama_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_mistral_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_mistral_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_mistral_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_openai_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_openai_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_openai_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_qwen_l_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_qwen_m_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_qwen_s_n200_v1 · silver | 0.000 | 200 | silver/cnn_dailymail_200 silver |
| cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_deepseek_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_deepseek_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_gemma_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_gemma_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_glm_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 197 | judge judge-summ-pick-v1 |
| cnn_glm_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_glm_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 197 | judge judge-summ-pick-v1 |
| cnn_llama_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_llama_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_llama_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_mistral_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_mistral_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_mistral_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_openai_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_openai_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_openai_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v1 | 0.000 | 198 | judge judge-summ-pick-v1 |
| cnn_deepseek_m_n200_v1 · judged/judge-summ-pointwise-v1 | 0.000 | 200 | judge judge-summ-pointwise-v1 |
| cnn_anthropic_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_anthropic_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_anthropic_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_deepseek_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_deepseek_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_deepseek_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_gemma_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_gemma_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_gemma_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_glm_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 196 | judge judge-summ-v1 |
| cnn_glm_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_glm_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 196 | judge judge-summ-v1 |
| cnn_llama_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_llama_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_llama_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_mistral_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_mistral_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_mistral_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_openai_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_openai_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_openai_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_qwen_l_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_qwen_m_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_qwen_s_n200_v1 · judged/judge-summ-v1 | 0.000 | 197 | judge judge-summ-v1 |
| cnn_anthropic_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_anthropic_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_anthropic_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_deepseek_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_deepseek_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_deepseek_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_gemma_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_gemma_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_gemma_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_glm_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 199 | judge judge-summ-v2 |
| cnn_glm_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_glm_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 199 | judge judge-summ-v2 |
| cnn_llama_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_llama_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_llama_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_mistral_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_mistral_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_mistral_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_openai_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_openai_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_openai_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_qwen_l_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_qwen_m_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |
| cnn_qwen_s_n200_v1 · judged/judge-summ-v2 | 0.000 | 200 | judge judge-summ-v2 |