| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f | 0.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 5f2c057c | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 5f2c057c | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 77adc97b | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 77adc97b | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 77adc97b | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored cd35dc1f | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored cd35dc1f | 0.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 3d3a6afd | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 5f2c057c | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 77adc97b | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored cd35dc1f | 0.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 0.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd | 0.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 5f2c057c | 0.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 77adc97b | 0.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored cd35dc1f | 0.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 3d3a6afd | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 5f2c057c | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f | 0.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 | 0.585 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats | 0.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 | 0.610 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 | 0.610 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 | 0.610 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 | 0.610 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 | 0.626 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 | 0.626 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 | 0.626 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 | 0.631 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd | 0.631 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c | 0.631 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 3d3a6afd | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 5f2c057c | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 5f2c057c | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 77adc97b | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 77adc97b | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored cd35dc1f | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored cd35dc1f | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 0.646 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 77adc97b | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f | 0.662 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 77adc97b | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f | 0.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 77adc97b | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f | 0.692 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 3d3a6afd | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 5f2c057c | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 77adc97b | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored cd35dc1f | 0.708 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 3d3a6afd | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 77adc97b | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored cd35dc1f | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 5f2c057c | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 5f2c057c | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 77adc97b | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 77adc97b | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored cd35dc1f | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored cd35dc1f | 0.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 | 0.764 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 | 0.764 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 | 0.764 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 | 0.764 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 | 0.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd | 0.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 5f2c057c | 0.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 77adc97b | 0.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored cd35dc1f | 0.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 3d3a6afd | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 5f2c057c | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 5f2c057c | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 77adc97b | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored cd35dc1f | 0.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f | 0.815 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 | 0.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 3d3a6afd | 0.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 5f2c057c | 0.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 77adc97b | 0.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored cd35dc1f | 0.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 5f2c057c | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 77adc97b | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f | 0.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 | 0.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 0.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c | 0.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b | 0.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f | 0.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 3d3a6afd | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 5f2c057c | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 77adc97b | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f | 0.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c | 1.015 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b | 1.015 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 | 1.046 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c | 1.046 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 77adc97b | 1.046 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f | 1.046 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 5f2c057c | 1.077 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 77adc97b | 1.077 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored cd35dc1f | 1.077 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c | 1.092 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c | 1.092 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b | 1.092 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b | 1.092 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f | 1.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 | 1.154 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 3d3a6afd | 1.154 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 5f2c057c | 1.154 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 77adc97b | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 | 1.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd | 1.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c | 1.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 | 1.354 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd | 1.354 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c | 1.354 | 65 | gold/orrery_triage_v1_labelled gold |