| triage_stub_dismiss_v1 | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 3d3a6afd | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 3d3a6afd | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 5f2c057c | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 5f2c057c | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 77adc97b | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 77adc97b | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored cd35dc1f | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored cd35dc1f | 1000.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 | 2618.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c | 2618.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b | 2618.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f | 2618.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 | 2720.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd | 2720.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c | 2720.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 | 2799.6 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c | 2799.6 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b | 2799.6 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f | 2799.6 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 | 2849.9 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c | 2849.9 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b | 2849.9 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f | 2849.9 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 | 2854.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd | 2854.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c | 2854.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 | 2897.6 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c | 2897.6 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b | 2897.6 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f | 2897.6 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 | 2929.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd | 2929.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 5f2c057c | 2929.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 77adc97b | 2929.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored cd35dc1f | 2929.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 | 2976.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd | 2976.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c | 2976.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 | 3018.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd | 3018.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c | 3018.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 | 3047.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd | 3047.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c | 3047.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 | 3081.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 3081.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c | 3081.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b | 3081.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f | 3081.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 | 3156.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 3156.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c | 3156.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b | 3156.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f | 3156.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 | 3253.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c | 3253.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b | 3253.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f | 3253.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 | 3334.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c | 3334.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b | 3334.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f | 3334.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 | 3395.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c | 3395.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 77adc97b | 3395.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f | 3395.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 | 3460.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c | 3460.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 77adc97b | 3460.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f | 3460.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 | 3463.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd | 3463.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c | 3463.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b | 3463.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f | 3463.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 | 3538.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c | 3538.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b | 3538.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f | 3538.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · repeats ×3 | 3577.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 | 3577.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 | 3577.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 | 3577.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 | 3577.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 | 3798.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 5f2c057c | 3798.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 77adc97b | 3798.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored cd35dc1f | 3798.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · repeats ×3 | 3835.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 | 3835.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 | 3835.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 | 3835.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 | 3835.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 | 3838.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd | 3838.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c | 3838.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b | 3838.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f | 3838.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 | 3880.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd | 3880.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c | 3880.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 | 3944.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd | 3944.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 5f2c057c | 3944.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 | 3980.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd | 3980.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c | 3980.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 | 3984.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c | 3984.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b | 3984.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f | 3984.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 | 3999.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd | 3999.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 5f2c057c | 3999.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 | 4000.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c | 4000.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 77adc97b | 4000.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f | 4000.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 | 4034.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 5f2c057c | 4034.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 77adc97b | 4034.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored cd35dc1f | 4034.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 | 4045.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c | 4045.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 77adc97b | 4045.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f | 4045.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · repeats ×3 | 4067.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 | 4067.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 | 4067.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 | 4067.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 | 4085.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd | 4085.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c | 4085.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 | 4099.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd | 4099.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c | 4099.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 | 4140.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd | 4140.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c | 4140.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 | 4166.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c | 4166.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b | 4166.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f | 4166.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 | 4171.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd | 4171.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c | 4171.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 | 4192.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd | 4192.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c | 4192.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 | 4236.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 3d3a6afd | 4236.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 5f2c057c | 4236.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 77adc97b | 4236.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored cd35dc1f | 4236.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 | 4250.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 3d3a6afd | 4250.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 5f2c057c | 4250.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 | 4284.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c | 4284.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b | 4284.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f | 4284.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 | 4307.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd | 4307.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c | 4307.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b | 4307.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f | 4307.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 | 4416.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 5f2c057c | 4416.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 77adc97b | 4416.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored cd35dc1f | 4416.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 | 4447.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 3d3a6afd | 4447.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 5f2c057c | 4447.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 | 4579.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 5f2c057c | 4579.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 77adc97b | 4579.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored cd35dc1f | 4579.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 | 4610.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd | 4610.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c | 4610.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b | 4610.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f | 4610.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · repeats ×3 | 4707.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 | 4707.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 | 4707.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 | 4707.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 | 4707.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats | 4765.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 | 4803.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 4803.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 4803.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 4803.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 | 4842.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd | 4842.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c | 4842.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 | 4845.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 4845.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 4845.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 4845.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 | 4856.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 4856.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 4856.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 4856.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 | 4891.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 4891.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 4891.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 4891.7 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 | 4966.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 4966.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 4966.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 4966.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 | 5013.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 3d3a6afd | 5013.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 5f2c057c | 5013.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 | 5014.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 5014.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 5014.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 | 5150.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 5f2c057c | 5150.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 77adc97b | 5150.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored cd35dc1f | 5150.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 | 5176.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 3d3a6afd | 5176.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 5f2c057c | 5176.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 | 5202.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 5202.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 5202.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 | 5222.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 3d3a6afd | 5222.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 5f2c057c | 5222.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 | 5275.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd | 5275.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 5f2c057c | 5275.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 77adc97b | 5275.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored cd35dc1f | 5275.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 | 5321.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd | 5321.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c | 5321.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 77adc97b | 5321.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f | 5321.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 | 5333.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd | 5333.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 5f2c057c | 5333.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 77adc97b | 5333.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored cd35dc1f | 5333.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 | 5386.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 5386.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 5386.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 | 5431.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd | 5431.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c | 5431.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 77adc97b | 5431.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f | 5431.3 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 | 5531.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd | 5531.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 5f2c057c | 5531.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 77adc97b | 5531.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored cd35dc1f | 5531.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 | 5594.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd | 5594.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 5f2c057c | 5594.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 77adc97b | 5594.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored cd35dc1f | 5594.1 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 | 5611.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd | 5611.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c | 5611.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b | 5611.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f | 5611.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 | 5666.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 5666.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c | 5666.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b | 5666.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f | 5666.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 | 5700.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd | 5700.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c | 5700.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 77adc97b | 5700.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f | 5700.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 | 5830.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 5830.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c | 5830.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b | 5830.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f | 5830.4 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 | 5871.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 5871.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c | 5871.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b | 5871.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f | 5871.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 | 5942.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd | 5942.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c | 5942.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 77adc97b | 5942.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f | 5942.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 | 5967.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 5967.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c | 5967.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b | 5967.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f | 5967.8 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 | 6008.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd | 6008.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c | 6008.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b | 6008.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f | 6008.0 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 | 6011.1 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd | 6011.1 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c | 6011.1 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b | 6011.1 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f | 6011.1 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 | 6077.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 6077.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 6077.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 | 6089.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 6089.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 6089.9 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 | 6090.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 6090.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 6090.2 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 | 6103.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 3d3a6afd | 6103.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 5f2c057c | 6103.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 77adc97b | 6103.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored cd35dc1f | 6103.6 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 | 6128.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd | 6128.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c | 6128.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b | 6128.5 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f | 6128.5 | 65 | gold/orrery_triage_v1_labelled gold |