eval-harness

activity

Activity and spend

When the work happened and what it cost, in the period: measured runs (repeats counted one by one), and what was billed, in USD and in tokens, to the systems under test and the judges. Each number is against the period before, and what moved most comes first, up or down.

all time, 2026-09-25 to 2026-11-02

01activity

293 measured runs (repeats counted one by one), by day and dataset.

0501002026-09-25 · cnn_dailymail_200: 4 runs2026-09-26 · cnn_dailymail_20: 2 runs2026-09-26 · cnn_dailymail_200: 22 runs2026-09-27 · ag_news_200: 28 runs2026-09-27 · dbpedia_280: 27 runs2026-09-28 · few_nerd_280: 27 runs2026-09-28 · scifact_200: 23 runs2026-09-29 · scifact_200: 3 runs2026-09-30 · ag_news_200: 5 runs2026-09-30 · cnn_dailymail_200: 9 runs2026-09-30 · dbpedia_280: 2 runs2026-10-01 · few_nerd_280: 1 runs2026-10-14 · cnn_dailymail_dm200: 4 runs2026-10-15 · cnn_dailymail_dm200: 1 runs2026-10-15 · summeval_100: 7 runs2026-10-18 · summeval_100: 26 runs2026-10-19 · summeval_100: 2 runs2026-10-23 · smoke_v1: 1 runs2026-10-30 · fleet_dedup_v1: 2 runs2026-10-30 · orrery_triage_v1_labelled: 51 runs2026-10-31 · orrery_triage_v1_labelled: 39 runs2026-11-01 · orrery_triage_v1_labelled: 1 runs2026-11-02 · summeval_100: 6 runs09-2510-1411-02

ag_news_200cnn_dailymail_20cnn_dailymail_200cnn_dailymail_dm200dbpedia_280few_nerd_280fleet_dedup_v1orrery_triage_v1_labelledscifact_200smoke_v1summeval_100

02spend

systems under test $32.15 · judges $13.50 · total $45.66

$0.0000$25.00$50.00systems under test: $32.15 by 2026-11-022026-09-25 · systems under test: $0.2569 so far2026-09-26 · systems under test: $5.74 so far2026-09-27 · systems under test: $7.49 so far2026-09-28 · systems under test: $12.61 so far2026-09-29 · systems under test: $13.04 so far2026-10-01 · systems under test: $13.08 so far2026-10-18 · systems under test: $20.10 so far2026-10-19 · systems under test: $20.23 so far2026-10-30 · systems under test: $30.15 so far2026-10-31 · systems under test: $31.97 so far2026-11-02 · systems under test: $32.15 so farjudges: $13.50 by 2026-11-022026-10-20 · judges: $0.4106 so far2026-10-21 · judges: $13.33 so far2026-11-02 · judges: $13.50 so far09-2510-1411-02

systems under testjudges

03by dataset

datasetruns in periodruns per dayspend in periodtokens in period
ag_news_200——
ag_news_20033——
cnn_dailymail_202——
cnn_dailymail_20035——
cnn_dailymail_dm2005——
dbpedia_28029——
dbpedia_560——
few_nerd_28028——
few_nerd_560——
fleet_dedup_v12——
orrery_triage_smoke0——
orrery_triage_v1_labelled91——
scifact_20026——
scifact_400——
smoke_v11——
summeval_10041——

04by arm

686 shown
armdatasetruns in periodspend in periodtokens in period
ag_anthropic_l_n200_v1ag_news_2001——
ag_anthropic_m_n200_v1ag_news_2001——
ag_anthropic_s_n200_v1ag_news_2001——
ag_bart_mnli_n200_v1ag_news_2001——
ag_bert_base_fy_n200_v1ag_news_2001——
ag_bert_base_ta_n200_v1ag_news_2001——
ag_bert_mini_n200_v1ag_news_2001——
ag_constant_n200_v1ag_news_2001——
ag_deepseek_l_n200_v1ag_news_2001——
ag_deepseek_m_n200_v1ag_news_2001——
ag_deepseek_s_n200_v1ag_news_2001——
ag_gemma_l_n200_v1ag_news_2001——
ag_gemma_m_n200_v1ag_news_2001——
ag_gemma_s_n200_v1ag_news_2001——
ag_glm_l_n200_v1ag_news_2001——
ag_glm_m_n200_v1ag_news_2001——
ag_glm_s_n200_v1ag_news_2001——
ag_keyword_n200_v1ag_news_2001——
ag_llama_l_n200_v1ag_news_2001——
ag_llama_m_n200_v1ag_news_2001——
ag_llama_s_n200_v1ag_news_2001——
ag_mistral_l_n200_v1ag_news_2001——
ag_mistral_m_n200_v1ag_news_2001——
ag_mistral_s_n200_v1ag_news_2001——
ag_openai_l_n200_v1ag_news_2001——
ag_openai_m_n200_v1ag_news_2001——
ag_openai_s_n200_v1ag_news_2001——
ag_qwen_l_n200_v1ag_news_2001——
ag_qwen_m_n200_v1ag_news_2001——
ag_qwen_s_n200_v1ag_news_2001——
ag_anthropic_l_n200_v1 · adjudicatedag_news_2000——
ag_anthropic_m_n200_v1 · adjudicatedag_news_2000——
ag_anthropic_s_n200_v1 · adjudicatedag_news_2000——
ag_bart_mnli_n200_v1 · adjudicatedag_news_2000——
ag_bert_base_fy_n200_v1 · adjudicatedag_news_2000——
ag_bert_base_ta_n200_v1 · adjudicatedag_news_2000——
ag_bert_mini_n200_v1 · adjudicatedag_news_2000——
ag_constant_n200_v1 · adjudicatedag_news_2000——
ag_deepseek_l_n200_v1 · adjudicatedag_news_2000——
ag_deepseek_m_n200_v1 · adjudicatedag_news_2000——
ag_deepseek_s_n200_v1 · adjudicatedag_news_2000——
ag_gemma_l_n200_v1 · adjudicatedag_news_2000——
ag_gemma_m_n200_v1 · adjudicatedag_news_2000——
ag_gemma_s_n200_v1 · adjudicatedag_news_2000——
ag_glm_l_n200_v1 · adjudicatedag_news_2000——
ag_glm_m_n200_v1 · adjudicatedag_news_2000——
ag_glm_s_n200_v1 · adjudicatedag_news_2000——
ag_keyword_n200_v1 · adjudicatedag_news_2000——
ag_llama_l_n200_v1 · adjudicatedag_news_2000——
ag_llama_m_n200_v1 · adjudicatedag_news_2000——
ag_llama_s_n200_v1 · adjudicatedag_news_2000——
ag_mistral_l_n200_v1 · adjudicatedag_news_2000——
ag_mistral_m_n200_v1 · adjudicatedag_news_2000——
ag_mistral_s_n200_v1 · adjudicatedag_news_2000——
ag_openai_l_n200_v1 · adjudicatedag_news_2000——
ag_openai_m_n200_v1 · adjudicatedag_news_2000——
ag_openai_s_n200_v1 · adjudicatedag_news_2000——
ag_qwen_l_n200_v1 · adjudicatedag_news_2000——
ag_qwen_m_n200_v1 · adjudicatedag_news_2000——
ag_qwen_s_n200_v1 · adjudicatedag_news_2000——
ag_bert_base_fy_n200_v1 · linuxag_news_2001——
ag_bert_base_ta_n200_v1 · linuxag_news_2001——
ag_bert_mini_n200_v1 · linuxag_news_2001——
cnn_bart_l_v1cnn_dailymail_201——
cnn_lead3_v1cnn_dailymail_201——
cnn_anthropic_l_n200_v1cnn_dailymail_2001——
cnn_anthropic_m_n200_v1cnn_dailymail_2001——
cnn_anthropic_s_n200_v1cnn_dailymail_2001——
cnn_bart_l_n200_v1cnn_dailymail_2001——
cnn_bart_l_xsum_n200_v1cnn_dailymail_2001——
cnn_bart_m_n200_v1cnn_dailymail_2001——
cnn_bart_s_n200_v1cnn_dailymail_2001——
cnn_deepseek_l_n200_v1cnn_dailymail_2001——
cnn_deepseek_m_n200_v1cnn_dailymail_2001——
cnn_deepseek_s_n200_v1cnn_dailymail_2001——
cnn_gemma_l_n200_v1cnn_dailymail_2001——
cnn_gemma_m_n200_v1cnn_dailymail_2001——
cnn_gemma_s_n200_v1cnn_dailymail_2001——
cnn_glm_l_n200_v1cnn_dailymail_2001——
cnn_glm_m_n200_v1cnn_dailymail_2001——
cnn_glm_s_n200_v1cnn_dailymail_2001——
cnn_lead3_n200_v1cnn_dailymail_2001——
cnn_llama_l_n200_v1cnn_dailymail_2001——
cnn_llama_m_n200_v1cnn_dailymail_2001——
cnn_llama_s_n200_v1cnn_dailymail_2001——
cnn_mistral_l_n200_v1cnn_dailymail_2001——
cnn_mistral_m_n200_v1cnn_dailymail_2001——
cnn_mistral_s_n200_v1cnn_dailymail_2001——
cnn_openai_l_n200_v1cnn_dailymail_2001——
cnn_openai_m_n200_v1cnn_dailymail_2001——
cnn_openai_s_n200_v1cnn_dailymail_2001——
cnn_qwen_l_n200_v1cnn_dailymail_2001——
cnn_qwen_m_n200_v1cnn_dailymail_2001——
cnn_qwen_s_n200_v1cnn_dailymail_2001——
cnn_bart_l_n200_v1 · linuxcnn_dailymail_2001——
cnn_bart_l_xsum_n200_v1 · linuxcnn_dailymail_2001——
cnn_bart_m_n200_v1 · linuxcnn_dailymail_2001——
cnn_bart_s_n200_v1 · linuxcnn_dailymail_2001——
cnn_lead3_n200_v1 · linuxcnn_dailymail_2001——
cnn_bart_s_n200_v1 · repeatscnn_dailymail_2001——
cnn_anthropic_l_n200_v1 · silvercnn_dailymail_2000——
cnn_anthropic_m_n200_v1 · silvercnn_dailymail_2000——
cnn_anthropic_s_n200_v1 · silvercnn_dailymail_2000——
cnn_bart_l_n200_v1 · silvercnn_dailymail_2000——
cnn_bart_l_xsum_n200_v1 · silvercnn_dailymail_2000——
cnn_bart_m_n200_v1 · silvercnn_dailymail_2000——
cnn_bart_s_n200_v1 · silvercnn_dailymail_2000——
cnn_deepseek_l_n200_v1 · silvercnn_dailymail_2000——
cnn_deepseek_m_n200_v1 · silvercnn_dailymail_2000——
cnn_deepseek_s_n200_v1 · silvercnn_dailymail_2000——
cnn_gemma_l_n200_v1 · silvercnn_dailymail_2000——
cnn_gemma_m_n200_v1 · silvercnn_dailymail_2000——
cnn_gemma_s_n200_v1 · silvercnn_dailymail_2000——
cnn_glm_l_n200_v1 · silvercnn_dailymail_2000——
cnn_glm_m_n200_v1 · silvercnn_dailymail_2000——
cnn_glm_s_n200_v1 · silvercnn_dailymail_2000——
cnn_lead3_n200_v1 · silvercnn_dailymail_2000——
cnn_llama_l_n200_v1 · silvercnn_dailymail_2000——
cnn_llama_m_n200_v1 · silvercnn_dailymail_2000——
cnn_llama_s_n200_v1 · silvercnn_dailymail_2000——
cnn_mistral_l_n200_v1 · silvercnn_dailymail_2000——
cnn_mistral_m_n200_v1 · silvercnn_dailymail_2000——
cnn_mistral_s_n200_v1 · silvercnn_dailymail_2000——
cnn_openai_l_n200_v1 · silvercnn_dailymail_2000——
cnn_openai_m_n200_v1 · silvercnn_dailymail_2000——
cnn_openai_s_n200_v1 · silvercnn_dailymail_2000——
cnn_qwen_l_n200_v1 · silvercnn_dailymail_2000——
cnn_qwen_m_n200_v1 · silvercnn_dailymail_2000——
cnn_qwen_s_n200_v1 · silvercnn_dailymail_2000——
cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_bart_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_bart_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_bart_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_deepseek_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_deepseek_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_gemma_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_gemma_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_glm_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_glm_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_glm_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_lead3_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_llama_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_llama_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_llama_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_mistral_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_mistral_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_mistral_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_openai_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_openai_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_openai_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v1cnn_dailymail_2000——
cnn_bart_l_n200_v1 · judged/judge-summ-pointwise-v1cnn_dailymail_2000——
cnn_deepseek_m_n200_v1 · judged/judge-summ-pointwise-v1cnn_dailymail_2000——
cnn_anthropic_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_anthropic_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_anthropic_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_bart_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_bart_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_bart_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_deepseek_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_deepseek_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_deepseek_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_gemma_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_gemma_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_gemma_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_glm_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_glm_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_glm_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_lead3_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_llama_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_llama_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_llama_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_mistral_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_mistral_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_mistral_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_openai_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_openai_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_openai_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_qwen_l_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_qwen_m_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_qwen_s_n200_v1 · judged/judge-summ-v1cnn_dailymail_2000——
cnn_anthropic_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_anthropic_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_anthropic_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_bart_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_bart_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_bart_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_deepseek_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_deepseek_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_deepseek_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_gemma_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_gemma_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_gemma_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_glm_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_glm_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_glm_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_lead3_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_llama_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_llama_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_llama_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_mistral_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_mistral_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_mistral_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_openai_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_openai_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_openai_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_qwen_l_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_qwen_m_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_qwen_s_n200_v1 · judged/judge-summ-v2cnn_dailymail_2000——
cnn_bart_l_dm200_v1cnn_dailymail_dm2001——
cnn_bart_l_xsum_dm200_v1cnn_dailymail_dm2001——
cnn_bart_m_dm200_v1cnn_dailymail_dm2001——
cnn_bart_s_dm200_v1cnn_dailymail_dm2001——
cnn_lead3_dm200_v1cnn_dailymail_dm2001——
db_anthropic_l_n200_v1dbpedia_2801——
db_anthropic_m_n200_v1dbpedia_2801——
db_anthropic_s_n200_v1dbpedia_2801——
db_bart_mnli_n200_v1dbpedia_2801——
db_bert_base_fy_n200_v1dbpedia_2801——
db_constant_n200_v1dbpedia_2801——
db_deepseek_l_n200_v1dbpedia_2801——
db_deepseek_m_n200_v1dbpedia_2801——
db_deepseek_s_n200_v1dbpedia_2801——
db_gemma_l_n200_v1dbpedia_2801——
db_gemma_m_n200_v1dbpedia_2801——
db_gemma_s_n200_v1dbpedia_2801——
db_glm_l_n200_v1dbpedia_2801——
db_glm_m_n200_v1dbpedia_2801——
db_glm_s_n200_v1dbpedia_2801——
db_keyword_n200_v1dbpedia_2801——
db_llama_l_n200_v1dbpedia_2801——
db_llama_m_n200_v1dbpedia_2801——
db_llama_s_n200_v1dbpedia_2801——
db_mistral_l_n200_v1dbpedia_2801——
db_mistral_m_n200_v1dbpedia_2801——
db_mistral_s_n200_v1dbpedia_2801——
db_openai_l_n200_v1dbpedia_2801——
db_openai_m_n200_v1dbpedia_2801——
db_openai_s_n200_v1dbpedia_2801——
db_qwen_l_n200_v1dbpedia_2801——
db_qwen_m_n200_v1dbpedia_2801——
db_qwen_s_n200_v1dbpedia_2801——
db_bert_base_fy_n200_v1 · linuxdbpedia_2801——
fn_anthropic_l_n200_v1few_nerd_2801——
fn_anthropic_m_n200_v1few_nerd_2801——
fn_anthropic_s_n200_v1few_nerd_2801——
fn_capitalized_n200_v1few_nerd_2801——
fn_deepseek_l_n200_v1few_nerd_2801——
fn_deepseek_m_n200_v1few_nerd_2801——
fn_deepseek_s_n200_v1few_nerd_2801——
fn_gemma_l_n200_v1few_nerd_2801——
fn_gemma_m_n200_v1few_nerd_2801——
fn_gemma_s_n200_v1few_nerd_2801——
fn_gliner_n200_v1few_nerd_2801——
fn_glm_l_n200_v1few_nerd_2801——
fn_glm_m_n200_v1few_nerd_2801——
fn_glm_s_n200_v1few_nerd_2801——
fn_llama_l_n200_v1few_nerd_2801——
fn_llama_m_n200_v1few_nerd_2801——
fn_llama_s_n200_v1few_nerd_2801——
fn_mistral_l_n200_v1few_nerd_2801——
fn_mistral_m_n200_v1few_nerd_2801——
fn_mistral_s_n200_v1few_nerd_2801——
fn_nothing_n200_v1few_nerd_2801——
fn_openai_l_n200_v1few_nerd_2801——
fn_openai_m_n200_v1few_nerd_2801——
fn_openai_s_n200_v1few_nerd_2801——
fn_qwen_l_n200_v1few_nerd_2801——
fn_qwen_m_n200_v1few_nerd_2801——
fn_qwen_s_n200_v1few_nerd_2801——
fn_span_marker_n200_v1few_nerd_2801——
dedup_guard_v1fleet_dedup_v11——
dedup_pinned_f07efa9_v1fleet_dedup_v11——
triage_baseline_pro_noreason_v1orrery_triage_v1_labelled1——
triage_baseline_pro_v1orrery_triage_v1_labelled1——
triage_deepseek_41flash_v1orrery_triage_v1_labelled1——
triage_deepseek_41flash_v2orrery_triage_v1_labelled1——
triage_gemini_35_flash_lite_v1orrery_triage_v1_labelled1——
triage_gemini_4_argon_v1orrery_triage_v1_labelled1——
triage_gpt_61_sol_v1orrery_triage_v1_labelled1——
triage_gpt_6_luna_v1orrery_triage_v1_labelled1——
triage_gpt_6_luna_v2orrery_triage_v1_labelled1——
triage_haiku_55_v1orrery_triage_v1_labelled1——
triage_hosted_gemma4_31b_v1orrery_triage_v1_labelled1——
triage_hosted_gemma4_31b_v2orrery_triage_v1_labelled1——
triage_hosted_gpt_oss_120b_v1orrery_triage_v1_labelled1——
triage_hosted_gpt_oss_120b_v2orrery_triage_v1_labelled1——
triage_hosted_mistral_medium_35_v1orrery_triage_v1_labelled1——
triage_hosted_qwen35_122b_v1orrery_triage_v1_labelled1——
triage_hosted_qwen35_122b_v2orrery_triage_v1_labelled1——
triage_hosted_qwen3_30b_a3b_v1orrery_triage_v1_labelled1——
triage_kimi_k31_pro_v1orrery_triage_v1_labelled1——
triage_kimi_k31_pro_v2orrery_triage_v1_labelled1——
triage_local_dgx_gemma4_12b_noreason_v1orrery_triage_v1_labelled1——
triage_local_dgx_gemma4_31b_v1orrery_triage_v1_labelled1——
triage_local_dgx_gemma4_31b_v2orrery_triage_v1_labelled1——
triage_local_dgx_gpt_oss_120b_v1orrery_triage_v1_labelled1——
triage_local_dgx_gpt_oss_120b_v2orrery_triage_v1_labelled1——
triage_local_dgx_gpt_oss_20b_v1orrery_triage_v1_labelled1——
triage_local_dgx_gpt_oss_20b_v2orrery_triage_v1_labelled1——
triage_local_dgx_llama31_8b_v1orrery_triage_v1_labelled1——
triage_local_dgx_llama4_scout_v1orrery_triage_v1_labelled1——
triage_local_dgx_ministral_3_14b_v1orrery_triage_v1_labelled1——
triage_local_dgx_mistral_medium_35_128b_v1orrery_triage_v1_labelled1——
triage_local_dgx_nemotron_35_bolt_e4b_v1orrery_triage_v1_labelled1——
triage_local_dgx_nemotron_35_bolt_e4b_v2orrery_triage_v1_labelled1——
triage_local_dgx_nemotron_35_lightning_30b_v1orrery_triage_v1_labelled1——
triage_local_dgx_nemotron_35_lightning_30b_v2orrery_triage_v1_labelled1——
triage_local_dgx_nemotron_35_super_120b_v1orrery_triage_v1_labelled1——
triage_local_dgx_nemotron_35_super_120b_v2orrery_triage_v1_labelled1——
triage_local_dgx_phi4_14b_v1orrery_triage_v1_labelled1——
triage_local_dgx_qwen35_122b_v1orrery_triage_v1_labelled1——
triage_local_dgx_qwen35_122b_v2orrery_triage_v1_labelled1——
triage_local_dgx_qwen38_27b_v1orrery_triage_v1_labelled1——
triage_local_dgx_qwen38_27b_v2orrery_triage_v1_labelled1——
triage_local_dgx_qwen3_30b_a3b_v1orrery_triage_v1_labelled1——
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1orrery_triage_v1_labelled1——
triage_local_mac_gemma4_12b_noreason_v1orrery_triage_v1_labelled1——
triage_local_mac_gemma4_31b_v1orrery_triage_v1_labelled1——
triage_local_mac_gemma4_31b_v2orrery_triage_v1_labelled1——
triage_local_mac_gpt_oss_20b_v1orrery_triage_v1_labelled1——
triage_local_mac_gpt_oss_20b_v2orrery_triage_v1_labelled1——
triage_local_mac_llama31_8b_v1orrery_triage_v1_labelled1——
triage_local_mac_ministral_3_14b_v1orrery_triage_v1_labelled1——
triage_local_mac_nemotron_35_bolt_e4b_v1orrery_triage_v1_labelled1——
triage_local_mac_nemotron_35_bolt_e4b_v2orrery_triage_v1_labelled1——
triage_local_mac_nemotron_35_lightning_30b_v1orrery_triage_v1_labelled1——
triage_local_mac_nemotron_35_lightning_30b_v2orrery_triage_v1_labelled1——
triage_local_mac_phi4_14b_v1orrery_triage_v1_labelled1——
triage_local_mac_qwen38_27b_v1orrery_triage_v1_labelled1——
triage_local_mac_qwen38_27b_v2orrery_triage_v1_labelled1——
triage_local_mac_qwen3_30b_a3b_v1orrery_triage_v1_labelled1——
triage_local_x3_gemma4_31b_v1orrery_triage_v1_labelled1——
triage_local_x3_gemma4_31b_v2orrery_triage_v1_labelled1——
triage_local_x3_gpt_oss_20b_v1orrery_triage_v1_labelled1——
triage_local_x3_gpt_oss_20b_v2orrery_triage_v1_labelled1——
triage_local_x3_llama31_8b_v1orrery_triage_v1_labelled1——
triage_local_x3_ministral_3_14b_v1orrery_triage_v1_labelled1——
triage_local_x3_nemotron_35_bolt_e4b_v1orrery_triage_v1_labelled1——
triage_local_x3_nemotron_35_bolt_e4b_v2orrery_triage_v1_labelled1——
triage_local_x3_nemotron_35_lightning_30b_v1orrery_triage_v1_labelled1——
triage_local_x3_nemotron_35_lightning_30b_v2orrery_triage_v1_labelled1——
triage_local_x3_phi4_14b_v1orrery_triage_v1_labelled1——
triage_local_x3_qwen38_27b_v1orrery_triage_v1_labelled1——
triage_local_x3_qwen38_27b_v2orrery_triage_v1_labelled1——
triage_local_x3_qwen3_30b_a3b_v1orrery_triage_v1_labelled1——
triage_mistral_large_4_v1orrery_triage_v1_labelled1——
triage_mistral_large_4_v2orrery_triage_v1_labelled1——
triage_sonnet_55_v1orrery_triage_v1_labelled1——
triage_stub_dismiss_v1orrery_triage_v1_labelled1——
triage_stub_escalate_v1orrery_triage_v1_labelled1——
triage_baseline_pro_v1 · repeats ×3orrery_triage_v1_labelled3——
triage_gpt_61_sol_v1 · repeats ×3orrery_triage_v1_labelled3——
triage_gpt_6_luna_v1 · repeats ×3orrery_triage_v1_labelled3——
triage_haiku_55_v1 · repeats ×3orrery_triage_v1_labelled3——
triage_local_x3_nemotron_35_bolt_e4b_v1 · repeatsorrery_triage_v1_labelled1——
triage_baseline_pro_noreason_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_deepseek_41flash_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_gemini_35_flash_lite_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_gemini_4_argon_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_gpt_6_luna_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_hosted_gemma4_31b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_hosted_qwen35_122b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_kimi_k31_pro_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_llama31_8b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_phi4_14b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_llama31_8b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_phi4_14b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_mistral_large_4_v2 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_sonnet_55_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_stub_dismiss_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_stub_escalate_v1 · rescored 3d3a6afdorrery_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3orrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3orrery_triage_v1_labelled0——
triage_baseline_pro_noreason_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_deepseek_41flash_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_deepseek_41flash_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_gemini_35_flash_lite_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_gemini_4_argon_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_gpt_6_luna_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_gpt_6_luna_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_haiku_55_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_gemma4_31b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_gemma4_31b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_mistral_medium_35_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_qwen35_122b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_qwen35_122b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_kimi_k31_pro_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_kimi_k31_pro_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_llama31_8b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_llama4_scout_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_phi4_14b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_gemma4_31b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_gemma4_31b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_llama31_8b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_phi4_14b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_qwen38_27b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_qwen38_27b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_gemma4_31b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_gemma4_31b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_llama31_8b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_phi4_14b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_qwen38_27b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_qwen38_27b_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_mistral_large_4_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_mistral_large_4_v2 · rescored 5f2c057correry_triage_v1_labelled0——
triage_sonnet_55_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_stub_dismiss_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_stub_escalate_v1 · rescored 5f2c057correry_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3orrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3orrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeatsorrery_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_deepseek_41flash_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_gemini_35_flash_lite_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_gemini_4_argon_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_gpt_6_luna_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_hosted_gemma4_31b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_hosted_gpt_oss_120b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_hosted_mistral_medium_35_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_hosted_qwen35_122b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_kimi_k31_pro_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_gemma4_31b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_llama31_8b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_llama4_scout_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_phi4_14b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_qwen35_122b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_qwen38_27b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_gemma4_31b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_llama31_8b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_ministral_3_14b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_phi4_14b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_qwen38_27b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_gemma4_31b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_llama31_8b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_ministral_3_14b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_phi4_14b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_qwen38_27b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_mistral_large_4_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_sonnet_55_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_stub_dismiss_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_stub_escalate_v1 · rescored 77adc97borrery_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3orrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored 77adc97b, repeats ×3orrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeatsorrery_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_deepseek_41flash_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_gemini_35_flash_lite_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_gemini_4_argon_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_gpt_6_luna_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_hosted_gemma4_31b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_hosted_mistral_medium_35_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_hosted_qwen35_122b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_kimi_k31_pro_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_llama31_8b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_llama4_scout_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_phi4_14b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_gemma4_31b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_llama31_8b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_phi4_14b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_qwen38_27b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_gemma4_31b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_llama31_8b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_phi4_14b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_qwen38_27b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_mistral_large_4_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_sonnet_55_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_stub_dismiss_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_stub_escalate_v1 · rescored cd35dc1forrery_triage_v1_labelled0——
triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3orrery_triage_v1_labelled0——
triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3orrery_triage_v1_labelled0——
triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3orrery_triage_v1_labelled0——
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeatsorrery_triage_v1_labelled0——
sf_bge_small_n200_v1scifact_2001——
sf_bm25_n200_v1scifact_2001——
sf_deepseek_m_n200_v1scifact_2001——
sf_deepseek_s_n200_v1scifact_2001——
sf_e5_base_n200_v1scifact_2001——
sf_first_k_n200_v1scifact_2001——
sf_gemma_l_n200_v1scifact_2001——
sf_gemma_m_n200_v1scifact_2001——
sf_gemma_s_n200_v1scifact_2001——
sf_glm_m_n200_v1scifact_2001——
sf_glm_s_n200_v1scifact_2001——
sf_llama_l_n200_v1scifact_2001——
sf_llama_m_n200_v1scifact_2001——
sf_llama_s_n200_v1scifact_2001——
sf_minilm_n200_v1scifact_2001——
sf_mistral_s_n200_v1scifact_2001——
sf_mpnet_n200_v1scifact_2001——
sf_qwen_s_n200_v1scifact_2001——
sf_random_n200_v1scifact_2001——
sf_glm_s_bm25first_n200_v1 · pairscifact_2001——
sf_glm_s_e5first_n200_v1 · pairscifact_2001——
sf_qwen_s_bm25first_n200_v1 · pairscifact_2001——
sf_qwen_s_e5first_n200_v1 · pairscifact_2001——
sf_llama_l_n200_v1 · repeatsscifact_2001——
sf_llama_s_n200_v1 · repeatsscifact_2001——
sf_qwen_s_n200_v1 · repeatsscifact_2001——
demo_v1smoke_v11——
se_anthropic_l_n100_v1summeval_1001——
se_anthropic_m_n100_v1summeval_1001——
se_anthropic_s_n100_v1summeval_1001——
se_bartscore_n100_v1summeval_1001——
se_coverage_n100_v1summeval_1001——
se_deepseek_l_n100_v1summeval_1001——
se_deepseek_m_n100_v1summeval_1001——
se_deepseek_s_n100_v1summeval_1001——
se_gemma_l_n100_pairwise_v1summeval_1001——
se_gemma_l_n100_pick_v1summeval_1001——
se_gemma_l_n100_v1summeval_1001——
se_gemma_m_n100_v1summeval_1001——
se_gemma_s_n100_v1summeval_1001——
se_glm_l_n100_v1summeval_1001——
se_glm_m_n100_v1summeval_1001——
se_glm_s_n100_v1summeval_1001——
se_length_n100_v1summeval_1001——
se_llama_l_n100_v1summeval_1001——
se_llama_m_n100_v1summeval_1001——
se_llama_s_n100_v1summeval_1001——
se_mistral_l_n100_v1summeval_1001——
se_mistral_m_n100_v1summeval_1001——
se_mistral_s_n100_v1summeval_1001——
se_openai_l_n100_v1summeval_1001——
se_openai_m_n100_v1summeval_1001——
se_openai_s_n100_v1summeval_1001——
se_qwen37max_n100_v1summeval_1001——
se_qwen_m_n100_v1summeval_1001——
se_qwen_s_n100_pairwise_v1summeval_1001——
se_qwen_s_n100_pick_v1summeval_1001——
se_qwen_s_n100_v1summeval_1001——
se_random_n100_pairwise_v1summeval_1001——
se_random_n100_pick_v1summeval_1001——
se_random_n100_v1summeval_1001——
se_rouge1_n100_v1summeval_1001——
se_rouge2_n100_v1summeval_1001——
se_rougeL_n100_v1summeval_1001——
se_unieval_n100_v1summeval_1001——
se_unievalpub_n100_v1summeval_1001——
se_gemma_l_pubtext_n100_v1 · pairsummeval_1001——
se_gemma_l_pubtextcw_n100_v1 · pairsummeval_1001——

05by kind

what was billedspend in periodtokens in period
systems under test——
judges——