| triage_stub_dismiss_v1 | 0.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 3d3a6afd | 0.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 5f2c057c | 0.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 77adc97b | 0.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored cd35dc1f | 0.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 3d3a6afd | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 5f2c057c | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f | 0.065 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 | 0.097 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd | 0.097 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c | 0.097 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b | 0.097 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f | 0.097 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 3d3a6afd | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 5f2c057c | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 5f2c057c | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c | 0.129 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 5f2c057c | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 5f2c057c | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 77adc97b | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored cd35dc1f | 0.161 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 5f2c057c | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 77adc97b | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored cd35dc1f | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.194 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 3d3a6afd | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 3d3a6afd | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 5f2c057c | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 5f2c057c | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 5f2c057c | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 77adc97b | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 77adc97b | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 77adc97b | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored cd35dc1f | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored cd35dc1f | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored cd35dc1f | 0.226 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 77adc97b | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f | 0.258 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 3d3a6afd | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 5f2c057c | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 77adc97b | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f | 0.290 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 5f2c057c | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 5f2c057c | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 77adc97b | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 77adc97b | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored cd35dc1f | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored cd35dc1f | 0.323 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 3d3a6afd | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats | 0.355 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 | 0.366 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 77adc97b | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 77adc97b | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f | 0.387 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · repeats ×3 | 0.409 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 | 0.409 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 | 0.409 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 | 0.409 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 5f2c057c | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 77adc97b | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 77adc97b | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored cd35dc1f | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 0.419 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 3d3a6afd | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 0.452 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f | 0.484 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · repeats ×3 | 0.505 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 | 0.505 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 | 0.505 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 | 0.505 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 | 0.505 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f | 0.516 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f | 0.581 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 5f2c057c | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 5f2c057c | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 77adc97b | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 77adc97b | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 77adc97b | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored cd35dc1f | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored cd35dc1f | 0.677 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 5f2c057c | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 5f2c057c | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 77adc97b | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 77adc97b | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored cd35dc1f | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored cd35dc1f | 0.774 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 0.806 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 | 0.839 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd | 0.839 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c | 0.839 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 77adc97b | 0.839 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f | 0.839 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 | 0.871 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd | 0.871 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c | 0.871 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 77adc97b | 0.871 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f | 0.871 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 | 1.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 3d3a6afd | 1.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 5f2c057c | 1.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 77adc97b | 1.000 | 31 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored cd35dc1f | 1.000 | 31 | gold/orrery_triage_v1_labelled gold |