| triage_local_dgx_nemotron_35_lightning_30b_v2 | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c | 3.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 | 2.938 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd | 2.938 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c | 2.938 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b | 2.938 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f | 2.938 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored 77adc97b | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored 77adc97b | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f | 2.877 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 | 2.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 2.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c | 2.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b | 2.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f | 2.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 5f2c057c | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored 77adc97b | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_phi4_14b_v1 · rescored cd35dc1f | 2.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 5f2c057c | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 5f2c057c | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored 77adc97b | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored 77adc97b | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_llama31_8b_v1 · rescored cd35dc1f | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_phi4_14b_v1 · rescored cd35dc1f | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f | 2.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 | 2.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd | 2.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c | 2.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored 77adc97b | 2.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f | 2.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 | 2.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd | 2.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 5f2c057c | 2.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored 77adc97b | 2.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_llama31_8b_v1 · rescored cd35dc1f | 2.769 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 | 2.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd | 2.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c | 2.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b | 2.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f | 2.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 | 2.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd | 2.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c | 2.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b | 2.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f | 2.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 | 2.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 2.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 2.677 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 | 2.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 2.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 2.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 | 2.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 5f2c057c | 2.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored 77adc97b | 2.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v1 · rescored cd35dc1f | 2.554 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 3d3a6afd | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_mistral_large_4_v2 · rescored 5f2c057c | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored 77adc97b | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f | 2.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 | 2.508 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 3d3a6afd | 2.508 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_noreason_v1 · rescored 5f2c057c | 2.508 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 | 2.492 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd | 2.492 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c | 2.492 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 | 2.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 2.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 2.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 2.400 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 | 2.385 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 2.385 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 2.385 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 2.385 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 | 2.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 2.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 2.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 2.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats | 2.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 | 2.308 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd | 2.308 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c | 2.308 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 | 2.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 3d3a6afd | 2.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 5f2c057c | 2.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored 77adc97b | 2.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_4_argon_v1 · rescored cd35dc1f | 2.292 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 | 2.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 2.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 2.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 2.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 | 2.246 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c | 2.246 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b | 2.246 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f | 2.246 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 | 2.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 3d3a6afd | 2.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v2 · rescored 5f2c057c | 2.138 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 | 2.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 5f2c057c | 2.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored 77adc97b | 2.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v1 · rescored cd35dc1f | 2.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 | 2.108 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c | 2.108 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b | 2.108 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f | 2.108 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 | 2.062 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 5f2c057c | 2.062 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored 77adc97b | 2.062 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v1 · rescored cd35dc1f | 2.062 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · repeats ×3 | 2.041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 | 2.041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 | 2.041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 | 2.041 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 | 2.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c | 2.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b | 2.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f | 2.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 | 2.015 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 3d3a6afd | 2.015 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_kimi_k31_pro_v2 · rescored 5f2c057c | 2.015 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 | 1.985 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd | 1.985 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c | 1.985 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 | 1.969 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd | 1.969 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c | 1.969 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f | 1.954 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 | 1.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd | 1.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c | 1.908 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 5f2c057c | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored 77adc97b | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored 77adc97b | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v1 · rescored cd35dc1f | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f | 1.892 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gemma4_31b_v2 · rescored 5f2c057c | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored 77adc97b | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f | 1.862 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 | 1.846 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd | 1.846 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c | 1.846 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 | 1.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd | 1.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c | 1.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b | 1.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f | 1.831 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · repeats ×3 | 1.810 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 | 1.810 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 | 1.810 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 | 1.810 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 | 1.810 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 | 1.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd | 1.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_qwen35_122b_v2 · rescored 5f2c057c | 1.800 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 3d3a6afd | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 5f2c057c | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored 77adc97b | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_sonnet_55_v1 · rescored cd35dc1f | 1.754 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 | 1.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 5f2c057c | 1.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored 77adc97b | 1.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_deepseek_41flash_v1 · rescored cd35dc1f | 1.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · repeats ×3 | 1.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 | 1.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 | 1.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 | 1.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 | 1.600 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 | 1.569 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c | 1.569 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b | 1.569 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f | 1.569 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 | 1.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 3d3a6afd | 1.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 5f2c057c | 1.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored 77adc97b | 1.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_baseline_pro_v1 · rescored cd35dc1f | 1.538 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 | 1.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c | 1.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored 77adc97b | 1.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f | 1.523 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 | 1.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c | 1.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored 77adc97b | 1.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f | 1.477 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 | 1.446 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c | 1.446 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b | 1.446 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f | 1.446 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 | 1.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 3d3a6afd | 1.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gpt_6_luna_v2 · rescored 5f2c057c | 1.415 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 | 1.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c | 1.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b | 1.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f | 1.338 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · repeats ×3 | 1.333 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 | 1.333 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 | 1.333 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 | 1.333 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 | 1.333 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 | 1.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 1.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c | 1.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b | 1.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f | 1.323 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 3d3a6afd | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 5f2c057c | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored 77adc97b | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_haiku_55_v1 · rescored cd35dc1f | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f | 1.277 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c | 1.262 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 | 1.200 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd | 1.200 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 5f2c057c | 1.200 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored 77adc97b | 1.200 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_gemini_35_flash_lite_v1 · rescored cd35dc1f | 1.200 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 | 1.185 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd | 1.185 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c | 1.185 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 | 1.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd | 1.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c | 1.123 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 | 1.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c | 1.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b | 1.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f | 1.031 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 3d3a6afd | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 3d3a6afd | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 5f2c057c | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 5f2c057c | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored 77adc97b | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored 77adc97b | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_dismiss_v1 · rescored cd35dc1f | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_stub_escalate_v1 · rescored cd35dc1f | 1.000 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f | 0.785 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 | 0.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c | 0.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b | 0.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f | 0.738 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |
| triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f | 0.723 | 65 | gold/orrery_triage_v1_labelled gold |