eval-harness

metric

table_miss

better
lower
kind
quality: measured against a reference or by a judge
decides
no goal
weighed by
no goal
recorded on
orrery_triage_v1_labelled

01what it measures, and how

1 when the model asked for a probe the item's frozen probe table does not hold.

A project explains its own metric at length with METRIC_DESCRIPTIONS = {"table_miss": {"summary": "…", "details": "…"}}.

02on orrery_triage_v1_labelled

gold/orrery_triage_v1_labelledtriage_baseline_pro_noreason_v1: 0triage_baseline_pro_v1: 0triage_deepseek_41flash_v1: 0triage_deepseek_41flash_v2: 0triage_gemini_35_flash_lite_v1: 0triage_gemini_4_argon_v1: 0triage_gpt_61_sol_v1: 0triage_gpt_6_luna_v1: 0triage_gpt_6_luna_v2: 0triage_haiku_55_v1: 0triage_hosted_gemma4_31b_v1: 0triage_hosted_gemma4_31b_v2: 0triage_hosted_gpt_oss_120b_v1: 0triage_hosted_gpt_oss_120b_v2: 0triage_hosted_mistral_medium_35_v1: 0triage_hosted_qwen35_122b_v1: 0triage_hosted_qwen35_122b_v2: 0triage_hosted_qwen3_30b_a3b_v1: 0triage_kimi_k31_pro_v1: 0triage_kimi_k31_pro_v2: 0triage_local_dgx_gemma4_12b_noreason_v1: 0triage_local_dgx_gemma4_31b_v1: 0triage_local_dgx_gemma4_31b_v2: 0triage_local_dgx_gpt_oss_120b_v1: 0triage_local_dgx_gpt_oss_120b_v2: 0triage_local_dgx_gpt_oss_20b_v1: 0triage_local_dgx_gpt_oss_20b_v2: 0triage_local_dgx_llama31_8b_v1: 0triage_local_dgx_ministral_3_14b_v1: 0triage_local_dgx_mistral_medium_35_128b_v1: 0triage_local_dgx_nemotron_35_bolt_e4b_v1: 0triage_local_dgx_nemotron_35_bolt_e4b_v2: 0triage_local_dgx_nemotron_35_lightning_30b_v1: 0triage_local_dgx_nemotron_35_lightning_30b_v2: 0triage_local_dgx_nemotron_35_super_120b_v1: 0triage_local_dgx_nemotron_35_super_120b_v2: 0triage_local_dgx_phi4_14b_v1: 0triage_local_dgx_qwen35_122b_v1: 0triage_local_dgx_qwen35_122b_v2: 0triage_local_dgx_qwen38_27b_v1: 0triage_local_dgx_qwen38_27b_v2: 0triage_local_dgx_qwen3_30b_a3b_v1: 0triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1: 0triage_local_mac_gemma4_12b_noreason_v1: 0triage_local_mac_gemma4_31b_v1: 0triage_local_mac_gemma4_31b_v2: 0triage_local_mac_gpt_oss_20b_v1: 0triage_local_mac_gpt_oss_20b_v2: 0triage_local_mac_llama31_8b_v1: 0triage_local_mac_ministral_3_14b_v1: 0triage_local_mac_nemotron_35_bolt_e4b_v1: 0triage_local_mac_nemotron_35_bolt_e4b_v2: 0triage_local_mac_nemotron_35_lightning_30b_v1: 0triage_local_mac_nemotron_35_lightning_30b_v2: 0triage_local_mac_phi4_14b_v1: 0triage_local_mac_qwen38_27b_v1: 0triage_local_mac_qwen38_27b_v2: 0triage_local_mac_qwen3_30b_a3b_v1: 0triage_local_x3_gemma4_31b_v1: 0triage_local_x3_gemma4_31b_v2: 0triage_local_x3_gpt_oss_20b_v1: 0triage_local_x3_gpt_oss_20b_v2: 0triage_local_x3_llama31_8b_v1: 0triage_local_x3_ministral_3_14b_v1: 0triage_local_x3_nemotron_35_bolt_e4b_v1: 0triage_local_x3_nemotron_35_bolt_e4b_v2: 0triage_local_x3_nemotron_35_lightning_30b_v1: 0triage_local_x3_nemotron_35_lightning_30b_v2: 0triage_local_x3_phi4_14b_v1: 0triage_local_x3_qwen38_27b_v1: 0triage_local_x3_qwen38_27b_v2: 0triage_local_x3_qwen3_30b_a3b_v1: 0triage_mistral_large_4_v1: 0triage_mistral_large_4_v2: 0triage_sonnet_55_v1: 0triage_stub_dismiss_v1: 0triage_stub_escalate_v1: 0triage_baseline_pro_v1 · repeats ×3: 0triage_gpt_61_sol_v1 · repeats ×3: 0triage_gpt_6_luna_v1 · repeats ×3: 0triage_haiku_55_v1 · repeats ×3: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats: 0triage_baseline_pro_noreason_v1 · rescored 3d3a6afd: 0triage_baseline_pro_v1 · rescored 3d3a6afd: 0triage_deepseek_41flash_v2 · rescored 3d3a6afd: 0triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd: 0triage_gemini_4_argon_v1 · rescored 3d3a6afd: 0triage_gpt_61_sol_v1 · rescored 3d3a6afd: 0triage_gpt_6_luna_v2 · rescored 3d3a6afd: 0triage_haiku_55_v1 · rescored 3d3a6afd: 0triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd: 0triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd: 0triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd: 0triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd: 0triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd: 0triage_kimi_k31_pro_v2 · rescored 3d3a6afd: 0triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd: 0triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd: 0triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd: 0triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd: 0triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd: 0triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd: 0triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd: 0triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd: 0triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd: 0triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd: 0triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd: 0triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd: 0triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd: 0triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd: 0triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd: 0triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd: 0triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd: 0triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd: 0triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd: 0triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd: 0triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd: 0triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd: 0triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd: 0triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd: 0triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd: 0triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd: 0triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd: 0triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd: 0triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd: 0triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd: 0triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd: 0triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd: 0triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd: 0triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd: 0triage_mistral_large_4_v2 · rescored 3d3a6afd: 0triage_sonnet_55_v1 · rescored 3d3a6afd: 0triage_stub_dismiss_v1 · rescored 3d3a6afd: 0triage_stub_escalate_v1 · rescored 3d3a6afd: 0triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3: 0triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3: 0triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3: 0triage_baseline_pro_noreason_v1 · rescored 5f2c057c: 0triage_baseline_pro_v1 · rescored 5f2c057c: 0triage_deepseek_41flash_v1 · rescored 5f2c057c: 0triage_deepseek_41flash_v2 · rescored 5f2c057c: 0triage_gemini_35_flash_lite_v1 · rescored 5f2c057c: 0triage_gemini_4_argon_v1 · rescored 5f2c057c: 0triage_gpt_61_sol_v1 · rescored 5f2c057c: 0triage_gpt_6_luna_v1 · rescored 5f2c057c: 0triage_gpt_6_luna_v2 · rescored 5f2c057c: 0triage_haiku_55_v1 · rescored 5f2c057c: 0triage_hosted_gemma4_31b_v1 · rescored 5f2c057c: 0triage_hosted_gemma4_31b_v2 · rescored 5f2c057c: 0triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c: 0triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c: 0triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c: 0triage_hosted_qwen35_122b_v1 · rescored 5f2c057c: 0triage_hosted_qwen35_122b_v2 · rescored 5f2c057c: 0triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c: 0triage_kimi_k31_pro_v1 · rescored 5f2c057c: 0triage_kimi_k31_pro_v2 · rescored 5f2c057c: 0triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c: 0triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c: 0triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c: 0triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c: 0triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c: 0triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c: 0triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c: 0triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c: 0triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c: 0triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c: 0triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c: 0triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c: 0triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c: 0triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c: 0triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c: 0triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c: 0triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c: 0triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c: 0triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c: 0triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c: 0triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c: 0triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c: 0triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c: 0triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c: 0triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c: 0triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c: 0triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c: 0triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c: 0triage_local_mac_llama31_8b_v1 · rescored 5f2c057c: 0triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c: 0triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c: 0triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c: 0triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c: 0triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c: 0triage_local_mac_phi4_14b_v1 · rescored 5f2c057c: 0triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c: 0triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c: 0triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c: 0triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c: 0triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c: 0triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c: 0triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c: 0triage_local_x3_llama31_8b_v1 · rescored 5f2c057c: 0triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c: 0triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c: 0triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c: 0triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c: 0triage_local_x3_phi4_14b_v1 · rescored 5f2c057c: 0triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c: 0triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c: 0triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c: 0triage_mistral_large_4_v1 · rescored 5f2c057c: 0triage_mistral_large_4_v2 · rescored 5f2c057c: 0triage_sonnet_55_v1 · rescored 5f2c057c: 0triage_stub_dismiss_v1 · rescored 5f2c057c: 0triage_stub_escalate_v1 · rescored 5f2c057c: 0triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3: 0triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3: 0triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3: 0triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats: 0triage_baseline_pro_v1 · rescored 77adc97b: 0triage_deepseek_41flash_v1 · rescored 77adc97b: 0triage_gemini_35_flash_lite_v1 · rescored 77adc97b: 0triage_gemini_4_argon_v1 · rescored 77adc97b: 0triage_gpt_61_sol_v1 · rescored 77adc97b: 0triage_gpt_6_luna_v1 · rescored 77adc97b: 0triage_haiku_55_v1 · rescored 77adc97b: 0triage_hosted_gemma4_31b_v1 · rescored 77adc97b: 0triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b: 0triage_hosted_mistral_medium_35_v1 · rescored 77adc97b: 0triage_hosted_qwen35_122b_v1 · rescored 77adc97b: 0triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b: 0triage_kimi_k31_pro_v1 · rescored 77adc97b: 0triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b: 0triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b: 0triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b: 0triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b: 0triage_local_dgx_llama31_8b_v1 · rescored 77adc97b: 0triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b: 0triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b: 0triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b: 0triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b: 0triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b: 0triage_local_dgx_phi4_14b_v1 · rescored 77adc97b: 0triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b: 0triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b: 0triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b: 0triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b: 0triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b: 0triage_local_mac_gemma4_31b_v1 · rescored 77adc97b: 0triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b: 0triage_local_mac_llama31_8b_v1 · rescored 77adc97b: 0triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b: 0triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b: 0triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b: 0triage_local_mac_phi4_14b_v1 · rescored 77adc97b: 0triage_local_mac_qwen38_27b_v1 · rescored 77adc97b: 0triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b: 0triage_local_x3_gemma4_31b_v1 · rescored 77adc97b: 0triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b: 0triage_local_x3_llama31_8b_v1 · rescored 77adc97b: 0triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b: 0triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b: 0triage_local_x3_phi4_14b_v1 · rescored 77adc97b: 0triage_local_x3_qwen38_27b_v1 · rescored 77adc97b: 0triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b: 0triage_mistral_large_4_v1 · rescored 77adc97b: 0triage_sonnet_55_v1 · rescored 77adc97b: 0triage_stub_dismiss_v1 · rescored 77adc97b: 0triage_stub_escalate_v1 · rescored 77adc97b: 0triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3: 0triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3: 0triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3: 0triage_haiku_55_v1 · rescored 77adc97b, repeats ×3: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats: 0triage_baseline_pro_v1 · rescored cd35dc1f: 0triage_deepseek_41flash_v1 · rescored cd35dc1f: 0triage_gemini_35_flash_lite_v1 · rescored cd35dc1f: 0triage_gemini_4_argon_v1 · rescored cd35dc1f: 0triage_gpt_61_sol_v1 · rescored cd35dc1f: 0triage_gpt_6_luna_v1 · rescored cd35dc1f: 0triage_haiku_55_v1 · rescored cd35dc1f: 0triage_hosted_gemma4_31b_v1 · rescored cd35dc1f: 0triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f: 0triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f: 0triage_hosted_qwen35_122b_v1 · rescored cd35dc1f: 0triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f: 0triage_kimi_k31_pro_v1 · rescored cd35dc1f: 0triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f: 0triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f: 0triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f: 0triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f: 0triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f: 0triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f: 0triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f: 0triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f: 0triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f: 0triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f: 0triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f: 0triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f: 0triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f: 0triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f: 0triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f: 0triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f: 0triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f: 0triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f: 0triage_local_mac_llama31_8b_v1 · rescored cd35dc1f: 0triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f: 0triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f: 0triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f: 0triage_local_mac_phi4_14b_v1 · rescored cd35dc1f: 0triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f: 0triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f: 0triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f: 0triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f: 0triage_local_x3_llama31_8b_v1 · rescored cd35dc1f: 0triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f: 0triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f: 0triage_local_x3_phi4_14b_v1 · rescored cd35dc1f: 0triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f: 0triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f: 0triage_mistral_large_4_v1 · rescored cd35dc1f: 0triage_sonnet_55_v1 · rescored cd35dc1f: 0triage_stub_dismiss_v1 · rescored cd35dc1f: 0triage_stub_escalate_v1 · rescored cd35dc1f: 0triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3: 0triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3: 0triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3: 0triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3: 0triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats: 0triage_local_dgx_llama4_scout_v1: 0.185triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd: 0.185triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c: 0.185triage_local_dgx_llama4_scout_v1 · rescored 77adc97b: 0.185triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f: 0.1850 · better0.185

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 table_missitemsscored against
triage_baseline_pro_noreason_v10.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v10.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v10.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v20.00065gold/orrery_triage_v1_labelled gold
triage_gemini_35_flash_lite_v10.00065gold/orrery_triage_v1_labelled gold
triage_gemini_4_argon_v10.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v10.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v10.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v20.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v10.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v10.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v20.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v10.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v20.00065gold/orrery_triage_v1_labelled gold
triage_hosted_mistral_medium_35_v10.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v10.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v20.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen3_30b_a3b_v10.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v10.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_12b_noreason_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama31_8b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_ministral_3_14b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_mistral_medium_35_128b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_phi4_14b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen3_30b_a3b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_12b_noreason_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_llama31_8b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_ministral_3_14b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_phi4_14b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen3_30b_a3b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_llama31_8b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_ministral_3_14b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_phi4_14b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v10.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v20.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen3_30b_a3b_v10.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v10.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v20.00065gold/orrery_triage_v1_labelled gold
triage_sonnet_55_v10.00065gold/orrery_triage_v1_labelled gold
triage_stub_dismiss_v10.00065gold/orrery_triage_v1_labelled gold
triage_stub_escalate_v10.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_noreason_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_4_argon_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v2 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_sonnet_55_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_stub_dismiss_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_stub_escalate_v1 · rescored 3d3a6afd0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_noreason_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_35_flash_lite_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_4_argon_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_llama31_8b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_phi4_14b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_llama31_8b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_phi4_14b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v2 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_sonnet_55_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_stub_dismiss_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_stub_escalate_v1 · rescored 5f2c057c0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored 5f2c057c, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_35_flash_lite_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_4_argon_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_mistral_medium_35_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama31_8b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_phi4_14b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_llama31_8b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_phi4_14b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_llama31_8b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_phi4_14b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_sonnet_55_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_stub_dismiss_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_stub_escalate_v1 · rescored 77adc97b0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored 77adc97b, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored 77adc97b, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_deepseek_41flash_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_35_flash_lite_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_gemini_4_argon_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gemma4_31b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen35_122b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_kimi_k31_pro_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_llama31_8b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_phi4_14b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_llama31_8b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_phi4_14b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_mistral_large_4_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_sonnet_55_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_stub_dismiss_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_stub_escalate_v1 · rescored cd35dc1f0.00065gold/orrery_triage_v1_labelled gold
triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_haiku_55_v1 · rescored cd35dc1f, repeats ×30.00065gold/orrery_triage_v1_labelled gold
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats0.00065gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama4_scout_v10.18565gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd0.18565gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c0.18565gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama4_scout_v1 · rescored 77adc97b0.18565gold/orrery_triage_v1_labelled gold
triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f0.18565gold/orrery_triage_v1_labelled gold