eval-harness

reference

silver/cnn_dailymail_200 silver

Promoted as silver: consistent, not a claim that any arm is right; good for ranking arms against each other.
Promoted from model the arm: cnn_anthropic_l_n200_v1, 2026-10-25: promoted before labels existed (0.6.0): its tier was given when it was made
The arm whose outputs these are is graded against its own outputs.

01what it is

tier
silver
dataset
cnn_dailymail_200
promoted from
model the arm: cnn_anthropic_l_n200_v1
why
promoted before labels existed (0.6.0): its tier was given when it was made
items
200
written by
cnn_anthropic_l_n200_v1
from the run
cnn_anthropic_l_n200_v1_20260926T063645Z
model
eval-opus-5
created
2026-10-25T16:22:49Z

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

armmetricmeanitems
cnn_anthropic_l_n200_v1 · silvercoverage1.000200inspect
cnn_anthropic_m_n200_v1 · silvercoverage0.491200inspect
cnn_deepseek_m_n200_v1 · silvercoverage0.471200inspect
cnn_anthropic_s_n200_v1 · silvercoverage0.469200inspect
cnn_deepseek_l_n200_v1 · silvercoverage0.399200inspect
cnn_qwen_l_n200_v1 · silvercoverage0.398200inspect
cnn_glm_m_n200_v1 · silvercoverage0.389200inspect
cnn_llama_s_n200_v1 · silvercoverage0.388200inspect
cnn_deepseek_s_n200_v1 · silvercoverage0.388200inspect
cnn_openai_s_n200_v1 · silvercoverage0.384200inspect
cnn_mistral_s_n200_v1 · silvercoverage0.382200inspect
cnn_qwen_m_n200_v1 · silvercoverage0.381200inspect
cnn_glm_l_n200_v1 · silvercoverage0.375200inspect
cnn_openai_l_n200_v1 · silvercoverage0.371200inspect
cnn_llama_l_n200_v1 · silvercoverage0.370200inspect
cnn_openai_m_n200_v1 · silvercoverage0.359200inspect
cnn_llama_m_n200_v1 · silvercoverage0.358200inspect
cnn_gemma_s_n200_v1 · silvercoverage0.350200inspect
cnn_gemma_m_n200_v1 · silvercoverage0.342200inspect
cnn_gemma_l_n200_v1 · silvercoverage0.342200inspect
cnn_mistral_l_n200_v1 · silvercoverage0.337200inspect
cnn_qwen_s_n200_v1 · silvercoverage0.334200inspect
cnn_mistral_m_n200_v1 · silvercoverage0.320200inspect
cnn_bart_m_n200_v1 · silvercoverage0.320200inspect
cnn_bart_l_n200_v1 · silvercoverage0.317200inspect
cnn_bart_s_n200_v1 · silvercoverage0.306200inspect
cnn_glm_s_n200_v1 · silvercoverage0.303200inspect
cnn_lead3_n200_v1 · silvercoverage0.300200inspect
cnn_bart_l_xsum_n200_v1 · silvercoverage0.137200inspect