eval-harness

reference

gold/orrery_triage_v1_labelled gold

Promoted as gold: the yardstick a decision rests on.
Promoted from person gold_orrery_triage_v1_labelled, 2026-10-30: promoted before labels existed (0.6.0): its tier was given when it was made

01what it is

tier
gold
dataset
orrery_triage_v1_labelled
promoted from
person gold_orrery_triage_v1_labelled
why
promoted before labels existed (0.6.0): its tier was given when it was made
items
65
created
2026-10-30T12:24:57Z

02scored against it · 336

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
triage_hosted_qwen35_122b_v1false_dismiss0.29434inspect
triage_hosted_mistral_medium_35_v1false_dismiss0.23534inspect
triage_baseline_pro_v1false_dismiss0.17634inspect
triage_deepseek_41flash_v1false_dismiss0.17634inspect
triage_hosted_gemma4_31b_v1false_dismiss0.17634inspect
triage_mistral_large_4_v1false_dismiss0.17634inspect
triage_baseline_pro_v1 · repeats ×3false_dismiss0.16734inspect
triage_hosted_gpt_oss_120b_v1false_dismiss0.14734inspect
triage_sonnet_55_v1false_dismiss0.14734inspect
triage_gemini_4_argon_v1false_dismiss0.11834inspect
triage_gpt_61_sol_v1false_dismiss0.11834inspect
triage_haiku_55_v1false_dismiss0.11834inspect
triage_kimi_k31_pro_v1false_dismiss0.11834inspect
triage_gpt_6_luna_v1 · repeats ×3false_dismiss0.11834inspect
triage_haiku_55_v1 · repeats ×3false_dismiss0.11834inspect
triage_gemini_35_flash_lite_v1false_dismiss0.08834inspect
triage_gpt_6_luna_v1false_dismiss0.08834inspect
triage_gpt_61_sol_v1 · repeats ×3false_dismiss0.08834inspect
triage_local_x3_llama31_8b_v1false_dismiss0.00034inspect
triage_local_dgx_qwen35_122b_v2triage_cost1.35465inspect
triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afdtriage_cost1.35465inspect
triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057ctriage_cost1.35465inspect
triage_local_x3_qwen38_27b_v2triage_cost1.29265inspect
triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afdtriage_cost1.29265inspect
triage_local_x3_qwen38_27b_v2 · rescored 5f2c057ctriage_cost1.29265inspect
triage_local_dgx_llama4_scout_v1triage_cost1.26265inspect
triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afdtriage_cost1.26265inspect
triage_local_dgx_llama4_scout_v1 · rescored 5f2c057ctriage_cost1.26265inspect
triage_local_dgx_llama4_scout_v1 · rescored 77adc97btriage_cost1.26265inspect
triage_local_dgx_llama4_scout_v1 · rescored cd35dc1ftriage_cost1.26265inspect
triage_baseline_pro_noreason_v1triage_cost1.15465inspect
triage_baseline_pro_noreason_v1 · rescored 3d3a6afdtriage_cost1.15465inspect
triage_baseline_pro_noreason_v1 · rescored 5f2c057ctriage_cost1.15465inspect
triage_local_dgx_qwen35_122b_v1triage_cost1.13865inspect
triage_local_dgx_qwen38_27b_v2triage_cost1.13865inspect
triage_local_mac_qwen38_27b_v2triage_cost1.13865inspect
triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afdtriage_cost1.13865inspect
triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afdtriage_cost1.13865inspect
triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057ctriage_cost1.13865inspect
triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057ctriage_cost1.13865inspect
triage_local_mac_qwen38_27b_v2 · rescored 5f2c057ctriage_cost1.13865inspect
triage_local_dgx_qwen35_122b_v1 · rescored 77adc97btriage_cost1.13865inspect
triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1ftriage_cost1.13865inspect
triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057ctriage_cost1.09265inspect
triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057ctriage_cost1.09265inspect
triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97btriage_cost1.09265inspect
triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97btriage_cost1.09265inspect
triage_hosted_qwen35_122b_v1 · rescored 5f2c057ctriage_cost1.07765inspect
triage_hosted_qwen35_122b_v1 · rescored 77adc97btriage_cost1.07765inspect
triage_hosted_qwen35_122b_v1 · rescored cd35dc1ftriage_cost1.07765inspect
triage_local_mac_qwen38_27b_v1triage_cost1.04665inspect
triage_local_mac_qwen38_27b_v1 · rescored 5f2c057ctriage_cost1.04665inspect
triage_local_mac_qwen38_27b_v1 · rescored 77adc97btriage_cost1.04665inspect
triage_local_mac_qwen38_27b_v1 · rescored cd35dc1ftriage_cost1.04665inspect
triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057ctriage_cost1.01565inspect
triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97btriage_cost1.01565inspect
triage_local_dgx_mistral_medium_35_128b_v1triage_cost1.00065inspect
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afdtriage_cost1.00065inspect
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057ctriage_cost1.00065inspect
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97btriage_cost1.00065inspect
triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1ftriage_cost1.00065inspect
triage_deepseek_41flash_v2triage_cost0.90865inspect
triage_local_x3_qwen38_27b_v1triage_cost0.90865inspect
triage_deepseek_41flash_v2 · rescored 3d3a6afdtriage_cost0.90865inspect
triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afdtriage_cost0.90865inspect
triage_deepseek_41flash_v2 · rescored 5f2c057ctriage_cost0.90865inspect
triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057ctriage_cost0.90865inspect
triage_local_x3_qwen38_27b_v1 · rescored 5f2c057ctriage_cost0.90865inspect
triage_local_mac_ministral_3_14b_v1 · rescored 77adc97btriage_cost0.90865inspect
triage_local_x3_qwen38_27b_v1 · rescored 77adc97btriage_cost0.90865inspect
triage_local_x3_qwen38_27b_v1 · rescored cd35dc1ftriage_cost0.90865inspect
triage_local_dgx_qwen3_30b_a3b_v1triage_cost0.89265inspect
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afdtriage_cost0.89265inspect
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057ctriage_cost0.89265inspect
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97btriage_cost0.89265inspect
triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1ftriage_cost0.89265inspect
triage_hosted_qwen35_122b_v2triage_cost0.87765inspect
triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afdtriage_cost0.87765inspect
triage_hosted_qwen35_122b_v2 · rescored 3d3a6afdtriage_cost0.87765inspect
triage_hosted_mistral_medium_35_v1 · rescored 5f2c057ctriage_cost0.87765inspect
triage_hosted_qwen35_122b_v2 · rescored 5f2c057ctriage_cost0.87765inspect
triage_hosted_mistral_medium_35_v1 · rescored 77adc97btriage_cost0.87765inspect
triage_hosted_mistral_medium_35_v1 · rescored cd35dc1ftriage_cost0.87765inspect
triage_stub_dismiss_v1triage_cost0.86265inspect
triage_stub_dismiss_v1 · rescored 3d3a6afdtriage_cost0.86265inspect
triage_stub_dismiss_v1 · rescored 5f2c057ctriage_cost0.86265inspect
triage_stub_dismiss_v1 · rescored 77adc97btriage_cost0.86265inspect
triage_stub_dismiss_v1 · rescored cd35dc1ftriage_cost0.86265inspect
triage_local_dgx_ministral_3_14b_v1triage_cost0.83165inspect
triage_local_dgx_qwen38_27b_v1triage_cost0.83165inspect
triage_local_mac_ministral_3_14b_v1triage_cost0.83165inspect
triage_local_mac_qwen3_30b_a3b_v1triage_cost0.83165inspect
triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afdtriage_cost0.83165inspect
triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afdtriage_cost0.83165inspect
triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057ctriage_cost0.83165inspect
triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057ctriage_cost0.83165inspect
triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057ctriage_cost0.83165inspect
triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97btriage_cost0.83165inspect
triage_local_dgx_qwen38_27b_v1 · rescored 77adc97btriage_cost0.83165inspect
triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97btriage_cost0.83165inspect
triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1ftriage_cost0.83165inspect
triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1ftriage_cost0.83165inspect
triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1ftriage_cost0.83165inspect
triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1ftriage_cost0.83165inspect
triage_local_x3_gpt_oss_20b_v2triage_cost0.81565inspect
triage_local_x3_ministral_3_14b_v1triage_cost0.81565inspect
triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afdtriage_cost0.81565inspect
triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afdtriage_cost0.81565inspect
triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057ctriage_cost0.81565inspect
triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057ctriage_cost0.81565inspect
triage_local_x3_ministral_3_14b_v1 · rescored 77adc97btriage_cost0.81565inspect
triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1ftriage_cost0.81565inspect
triage_local_mac_gemma4_31b_v2triage_cost0.80065inspect
triage_mistral_large_4_v2triage_cost0.80065inspect
triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afdtriage_cost0.80065inspect
triage_mistral_large_4_v2 · rescored 3d3a6afdtriage_cost0.80065inspect
triage_local_mac_gemma4_31b_v2 · rescored 5f2c057ctriage_cost0.80065inspect
triage_mistral_large_4_v1 · rescored 5f2c057ctriage_cost0.80065inspect
triage_mistral_large_4_v2 · rescored 5f2c057ctriage_cost0.80065inspect
triage_mistral_large_4_v1 · rescored 77adc97btriage_cost0.80065inspect
triage_mistral_large_4_v1 · rescored cd35dc1ftriage_cost0.80065inspect
triage_baseline_pro_v1 · rescored 3d3a6afdtriage_cost0.78565inspect
triage_baseline_pro_v1 · rescored 5f2c057ctriage_cost0.78565inspect
triage_baseline_pro_v1 · rescored 77adc97btriage_cost0.78565inspect
triage_baseline_pro_v1 · rescored cd35dc1ftriage_cost0.78565inspect
triage_local_x3_phi4_14b_v1triage_cost0.76965inspect
triage_local_x3_phi4_14b_v1 · rescored 3d3a6afdtriage_cost0.76965inspect
triage_local_x3_phi4_14b_v1 · rescored 5f2c057ctriage_cost0.76965inspect
triage_local_x3_phi4_14b_v1 · rescored 77adc97btriage_cost0.76965inspect
triage_local_x3_phi4_14b_v1 · rescored cd35dc1ftriage_cost0.76965inspect
triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3triage_cost0.76465inspect
triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3triage_cost0.76465inspect
triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3triage_cost0.76465inspect
triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3triage_cost0.76465inspect
triage_local_mac_nemotron_35_bolt_e4b_v1triage_cost0.75465inspect
triage_local_mac_phi4_14b_v1triage_cost0.75465inspect
triage_local_mac_phi4_14b_v1 · rescored 3d3a6afdtriage_cost0.75465inspect
triage_deepseek_41flash_v1 · rescored 5f2c057ctriage_cost0.75465inspect
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057ctriage_cost0.75465inspect
triage_local_mac_phi4_14b_v1 · rescored 5f2c057ctriage_cost0.75465inspect
triage_deepseek_41flash_v1 · rescored 77adc97btriage_cost0.75465inspect
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97btriage_cost0.75465inspect
triage_local_mac_phi4_14b_v1 · rescored 77adc97btriage_cost0.75465inspect
triage_deepseek_41flash_v1 · rescored cd35dc1ftriage_cost0.75465inspect
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1ftriage_cost0.75465inspect
triage_local_mac_phi4_14b_v1 · rescored cd35dc1ftriage_cost0.75465inspect
triage_hosted_gemma4_31b_v2triage_cost0.72365inspect
triage_kimi_k31_pro_v2triage_cost0.72365inspect
triage_local_dgx_gemma4_31b_v2triage_cost0.72365inspect
triage_local_dgx_gpt_oss_20b_v2triage_cost0.72365inspect
triage_local_x3_qwen3_30b_a3b_v1triage_cost0.72365inspect
triage_hosted_gemma4_31b_v2 · rescored 3d3a6afdtriage_cost0.72365inspect
triage_kimi_k31_pro_v2 · rescored 3d3a6afdtriage_cost0.72365inspect
triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afdtriage_cost0.72365inspect
triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afdtriage_cost0.72365inspect
triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afdtriage_cost0.72365inspect
triage_hosted_gemma4_31b_v1 · rescored 5f2c057ctriage_cost0.72365inspect
triage_hosted_gemma4_31b_v2 · rescored 5f2c057ctriage_cost0.72365inspect
triage_kimi_k31_pro_v2 · rescored 5f2c057ctriage_cost0.72365inspect
triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057ctriage_cost0.72365inspect
triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057ctriage_cost0.72365inspect
triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057ctriage_cost0.72365inspect
triage_hosted_gemma4_31b_v1 · rescored 77adc97btriage_cost0.72365inspect
triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97btriage_cost0.72365inspect
triage_hosted_gemma4_31b_v1 · rescored cd35dc1ftriage_cost0.72365inspect
triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1ftriage_cost0.72365inspect
triage_hosted_qwen3_30b_a3b_v1triage_cost0.70865inspect
triage_local_mac_gpt_oss_20b_v2triage_cost0.70865inspect
triage_local_x3_gemma4_31b_v2triage_cost0.70865inspect
triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afdtriage_cost0.70865inspect
triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afdtriage_cost0.70865inspect
triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afdtriage_cost0.70865inspect
triage_sonnet_55_v1 · rescored 3d3a6afdtriage_cost0.70865inspect
triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057ctriage_cost0.70865inspect
triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057ctriage_cost0.70865inspect
triage_local_x3_gemma4_31b_v2 · rescored 5f2c057ctriage_cost0.70865inspect
triage_sonnet_55_v1 · rescored 5f2c057ctriage_cost0.70865inspect
triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97btriage_cost0.70865inspect
triage_sonnet_55_v1 · rescored 77adc97btriage_cost0.70865inspect
triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1ftriage_cost0.70865inspect
triage_sonnet_55_v1 · rescored cd35dc1ftriage_cost0.70865inspect
triage_local_dgx_gpt_oss_120b_v1triage_cost0.69265inspect
triage_local_mac_nemotron_35_lightning_30b_v2triage_cost0.69265inspect
triage_local_x3_gemma4_31b_v1triage_cost0.69265inspect
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afdtriage_cost0.69265inspect
triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057ctriage_cost0.69265inspect
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057ctriage_cost0.69265inspect
triage_local_x3_gemma4_31b_v1 · rescored 5f2c057ctriage_cost0.69265inspect
triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97btriage_cost0.69265inspect
triage_local_x3_gemma4_31b_v1 · rescored 77adc97btriage_cost0.69265inspect
triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1ftriage_cost0.69265inspect
triage_local_x3_gemma4_31b_v1 · rescored cd35dc1ftriage_cost0.69265inspect
triage_local_dgx_gemma4_31b_v1triage_cost0.67765inspect
triage_local_dgx_nemotron_35_lightning_30b_v2triage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v1triage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v2triage_cost0.67765inspect
triage_local_mac_gemma4_31b_v1triage_cost0.67765inspect
triage_local_x3_nemotron_35_lightning_30b_v2triage_cost0.67765inspect
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afdtriage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afdtriage_cost0.67765inspect
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afdtriage_cost0.67765inspect
triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057ctriage_cost0.67765inspect
triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057ctriage_cost0.67765inspect
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057ctriage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057ctriage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057ctriage_cost0.67765inspect
triage_local_mac_gemma4_31b_v1 · rescored 5f2c057ctriage_cost0.67765inspect
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057ctriage_cost0.67765inspect
triage_hosted_gpt_oss_120b_v1 · rescored 77adc97btriage_cost0.67765inspect
triage_local_dgx_gemma4_31b_v1 · rescored 77adc97btriage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97btriage_cost0.67765inspect
triage_local_mac_gemma4_31b_v1 · rescored 77adc97btriage_cost0.67765inspect
triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1ftriage_cost0.67765inspect
triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1ftriage_cost0.67765inspect
triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1ftriage_cost0.67765inspect
triage_local_mac_gemma4_31b_v1 · rescored cd35dc1ftriage_cost0.67765inspect
triage_local_dgx_gpt_oss_120b_v2triage_cost0.66265inspect
triage_local_dgx_phi4_14b_v1triage_cost0.66265inspect
triage_gpt_61_sol_v1 · rescored 3d3a6afdtriage_cost0.66265inspect
triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afdtriage_cost0.66265inspect
triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afdtriage_cost0.66265inspect
triage_gpt_61_sol_v1 · rescored 5f2c057ctriage_cost0.66265inspect
triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057ctriage_cost0.66265inspect
triage_local_dgx_phi4_14b_v1 · rescored 5f2c057ctriage_cost0.66265inspect
triage_gpt_61_sol_v1 · rescored 77adc97btriage_cost0.66265inspect
triage_local_dgx_phi4_14b_v1 · rescored 77adc97btriage_cost0.66265inspect
triage_gpt_61_sol_v1 · rescored cd35dc1ftriage_cost0.66265inspect
triage_local_dgx_phi4_14b_v1 · rescored cd35dc1ftriage_cost0.66265inspect
triage_local_dgx_nemotron_35_bolt_e4b_v2triage_cost0.64665inspect
triage_local_dgx_nemotron_35_lightning_30b_v1triage_cost0.64665inspect
triage_local_mac_nemotron_35_lightning_30b_v1triage_cost0.64665inspect
triage_gemini_4_argon_v1 · rescored 3d3a6afdtriage_cost0.64665inspect
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afdtriage_cost0.64665inspect
triage_gemini_4_argon_v1 · rescored 5f2c057ctriage_cost0.64665inspect
triage_kimi_k31_pro_v1 · rescored 5f2c057ctriage_cost0.64665inspect
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057ctriage_cost0.64665inspect
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057ctriage_cost0.64665inspect
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057ctriage_cost0.64665inspect
triage_gemini_4_argon_v1 · rescored 77adc97btriage_cost0.64665inspect
triage_kimi_k31_pro_v1 · rescored 77adc97btriage_cost0.64665inspect
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97btriage_cost0.64665inspect
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97btriage_cost0.64665inspect
triage_gemini_4_argon_v1 · rescored cd35dc1ftriage_cost0.64665inspect
triage_kimi_k31_pro_v1 · rescored cd35dc1ftriage_cost0.64665inspect
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1ftriage_cost0.64665inspect
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1ftriage_cost0.64665inspect
triage_hosted_gpt_oss_120b_v2triage_cost0.63165inspect
triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afdtriage_cost0.63165inspect
triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057ctriage_cost0.63165inspect
triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3triage_cost0.62665inspect
triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3triage_cost0.62665inspect
triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3triage_cost0.62665inspect
triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3triage_cost0.61065inspect
triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3triage_cost0.61065inspect
triage_haiku_55_v1 · rescored 77adc97b, repeats ×3triage_cost0.61065inspect
triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3triage_cost0.61065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1triage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · repeatstriage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057ctriage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeatstriage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97btriage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeatstriage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1ftriage_cost0.60065inspect
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeatstriage_cost0.60065inspect
triage_local_dgx_gemma4_12b_noreason_v1triage_cost0.58565inspect
triage_local_mac_gemma4_12b_noreason_v1triage_cost0.58565inspect
triage_local_mac_nemotron_35_bolt_e4b_v2triage_cost0.58565inspect
triage_haiku_55_v1 · rescored 3d3a6afdtriage_cost0.58565inspect
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afdtriage_cost0.58565inspect
triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afdtriage_cost0.58565inspect
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afdtriage_cost0.58565inspect
triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3triage_cost0.58565inspect
triage_gpt_6_luna_v1 · rescored 5f2c057ctriage_cost0.58565inspect
triage_haiku_55_v1 · rescored 5f2c057ctriage_cost0.58565inspect
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057ctriage_cost0.58565inspect
triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057ctriage_cost0.58565inspect
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057ctriage_cost0.58565inspect
triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3triage_cost0.58565inspect
triage_gpt_6_luna_v1 · rescored 77adc97btriage_cost0.58565inspect
triage_haiku_55_v1 · rescored 77adc97btriage_cost0.58565inspect
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97btriage_cost0.58565inspect
triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97btriage_cost0.58565inspect
triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3triage_cost0.58565inspect
triage_gpt_6_luna_v1 · rescored cd35dc1ftriage_cost0.58565inspect
triage_haiku_55_v1 · rescored cd35dc1ftriage_cost0.58565inspect
triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1ftriage_cost0.58565inspect
triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1ftriage_cost0.58565inspect
triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3triage_cost0.58565inspect
triage_gpt_6_luna_v2triage_cost0.55465inspect
triage_local_mac_gpt_oss_20b_v1triage_cost0.55465inspect
triage_local_x3_nemotron_35_bolt_e4b_v2triage_cost0.55465inspect
triage_gpt_6_luna_v2 · rescored 3d3a6afdtriage_cost0.55465inspect
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afdtriage_cost0.55465inspect
triage_gpt_6_luna_v2 · rescored 5f2c057ctriage_cost0.55465inspect
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057ctriage_cost0.55465inspect
triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1ftriage_cost0.55465inspect
triage_gemini_35_flash_lite_v1 · rescored 3d3a6afdtriage_cost0.53865inspect
triage_gemini_35_flash_lite_v1 · rescored 5f2c057ctriage_cost0.53865inspect
triage_gemini_35_flash_lite_v1 · rescored 77adc97btriage_cost0.53865inspect
triage_gemini_35_flash_lite_v1 · rescored cd35dc1ftriage_cost0.53865inspect
triage_local_dgx_nemotron_35_bolt_e4b_v1triage_cost0.52365inspect
triage_local_x3_nemotron_35_lightning_30b_v1triage_cost0.52365inspect
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057ctriage_cost0.52365inspect
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057ctriage_cost0.52365inspect
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97btriage_cost0.52365inspect
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97btriage_cost0.52365inspect
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1ftriage_cost0.52365inspect
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1ftriage_cost0.52365inspect
triage_local_dgx_gpt_oss_20b_v1triage_cost0.47765inspect
triage_stub_escalate_v1triage_cost0.47765inspect
triage_stub_escalate_v1 · rescored 3d3a6afdtriage_cost0.47765inspect
triage_stub_escalate_v1 · rescored 5f2c057ctriage_cost0.47765inspect
triage_stub_escalate_v1 · rescored 77adc97btriage_cost0.47765inspect
triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1ftriage_cost0.47765inspect
triage_stub_escalate_v1 · rescored cd35dc1ftriage_cost0.47765inspect
triage_local_dgx_llama31_8b_v1triage_cost0.41565inspect
triage_local_mac_llama31_8b_v1triage_cost0.41565inspect
triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afdtriage_cost0.41565inspect
triage_local_mac_llama31_8b_v1 · rescored 3d3a6afdtriage_cost0.41565inspect
triage_local_x3_llama31_8b_v1 · rescored 3d3a6afdtriage_cost0.41565inspect
triage_local_dgx_llama31_8b_v1 · rescored 5f2c057ctriage_cost0.41565inspect
triage_local_mac_llama31_8b_v1 · rescored 5f2c057ctriage_cost0.41565inspect
triage_local_x3_llama31_8b_v1 · rescored 5f2c057ctriage_cost0.41565inspect
triage_local_dgx_llama31_8b_v1 · rescored 77adc97btriage_cost0.41565inspect
triage_local_mac_llama31_8b_v1 · rescored 77adc97btriage_cost0.41565inspect
triage_local_x3_llama31_8b_v1 · rescored 77adc97btriage_cost0.41565inspect
triage_local_dgx_llama31_8b_v1 · rescored cd35dc1ftriage_cost0.41565inspect
triage_local_mac_llama31_8b_v1 · rescored cd35dc1ftriage_cost0.41565inspect
triage_local_x3_llama31_8b_v1 · rescored cd35dc1ftriage_cost0.41565inspect
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1triage_cost0.40065inspect
triage_local_x3_gpt_oss_20b_v1triage_cost0.40065inspect
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afdtriage_cost0.40065inspect
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057ctriage_cost0.40065inspect
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97btriage_cost0.40065inspect
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1ftriage_cost0.40065inspect
triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1ftriage_cost0.40065inspect