| triage_local_dgx_gemma4_12b_noreason_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 | $0.000000 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 | $0.000000 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 | $0.000000 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 | $0.000000 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd | $0.000000 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c | $0.000000 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c | $0.000000 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c | $0.000000 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c | $0.000000 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b | $0.000000 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b | $0.000000 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b | $0.000000 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b | $0.000000 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f | $0.000000 | 50 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f | $0.000000 | 47 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f | $0.000000 | 64 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f | $0.000000 | 49 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats | $0.000000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 | $0.000355 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 3d3a6afd | $0.000355 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 5f2c057c | $0.000355 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 | $0.000627 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd | $0.000627 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c | $0.000627 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 | $0.000668 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 3d3a6afd | $0.000668 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 5f2c057c | $0.000668 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · repeats ×3 | $0.000684 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 | $0.000684 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 | $0.000684 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 | $0.000684 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 | $0.000700 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd | $0.000700 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c | $0.000700 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b | $0.000700 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f | $0.000700 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 | $0.000715 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c | $0.000715 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b | $0.000715 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f | $0.000715 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 | $0.000849 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c | $0.000849 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b | $0.000849 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f | $0.000849 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 | $0.000862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 5f2c057c | $0.000862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 77adc97b | $0.000862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored cd35dc1f | $0.000862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 | $0.000897 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd | $0.000897 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 5f2c057c | $0.000897 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 | $0.000903 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 5f2c057c | $0.000903 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 77adc97b | $0.000903 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored cd35dc1f | $0.000903 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 | $0.000998 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd | $0.000998 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c | $0.000998 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b | $0.000998 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f | $0.000998 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · repeats ×3 | $0.001024 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 | $0.001024 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 | $0.001024 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 | $0.001024 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 | $0.001024 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 | $0.001368 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd | $0.001368 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 5f2c057c | $0.001368 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 77adc97b | $0.001368 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored cd35dc1f | $0.001368 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 | $0.001654 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd | $0.001654 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 5f2c057c | $0.001654 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 | $0.003350 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 5f2c057c | $0.003350 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 77adc97b | $0.003350 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored cd35dc1f | $0.003350 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 | $0.004862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 3d3a6afd | $0.004862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 5f2c057c | $0.004862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 | $0.004992 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd | $0.004992 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c | $0.004992 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b | $0.004992 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f | $0.004992 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · repeats ×3 | $0.005104 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 | $0.005104 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 | $0.005104 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 | $0.005104 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 | $0.005104 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 | $0.006867 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 5f2c057c | $0.006867 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 77adc97b | $0.006867 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored cd35dc1f | $0.006867 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 | $0.006948 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 3d3a6afd | $0.006948 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 5f2c057c | $0.006948 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 | $0.010847 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd | $0.010847 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c | $0.010847 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b | $0.010847 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f | $0.010847 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · repeats ×3 | $0.010918 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 | $0.010918 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 | $0.010918 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 | $0.010918 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 | $0.010918 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 | $0.011539 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd | $0.011539 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c | $0.011539 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 77adc97b | $0.011539 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f | $0.011539 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 | $0.012041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 3d3a6afd | $0.012041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 5f2c057c | $0.012041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 | $0.013617 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 3d3a6afd | $0.013617 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 5f2c057c | $0.013617 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 77adc97b | $0.013617 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored cd35dc1f | $0.013617 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 | $0.019130 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 5f2c057c | $0.019130 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 77adc97b | $0.019130 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored cd35dc1f | $0.019130 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 | $0.022659 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 3d3a6afd | $0.022659 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 5f2c057c | $0.022659 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 77adc97b | $0.022659 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored cd35dc1f | $0.022659 | 65 | gold/orrery_triage_v1_labelled gold |