triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 served on dgx | triage_cost | 0.400 ↓ | 65 | $0.000000 · 4,813 tok | p50 7,347 · p95 11,042 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd served on dgx | triage_cost | 0.400 ↓ | 65 | $0.000000 · 4,813 tok | p50 7,347 · p95 11,042 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.400 ↓ | 65 | $0.000000 · 4,813 tok | p50 7,347 · p95 11,042 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b served on dgx | triage_cost | 0.400 ↓ | 65 | $0.000000 · 4,813 tok | p50 7,347 · p95 11,042 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.400 ↓ | 65 | $0.000000 · 4,813 tok | p50 7,347 · p95 11,042 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v1 served on x3 | triage_cost | 0.400 ↓ | 65 | $0.000000 · 3,619 tok | p50 16,207 · p95 29,798 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.400 ↓ | 65 | $0.000000 · 3,619 tok | p50 16,207 · p95 29,798 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama31_8b_v1 served on dgx | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,545 tok | p50 5,179 · p95 7,879 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd served on dgx | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,545 tok | p50 5,179 · p95 7,879 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,545 tok | p50 5,179 · p95 7,879 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama31_8b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,545 tok | p50 5,179 · p95 7,879 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,545 tok | p50 5,179 · p95 7,879 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_llama31_8b_v1 served on mac | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,565 tok | p50 7,125 · p95 10,541 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd served on mac | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,565 tok | p50 7,125 · p95 10,541 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_llama31_8b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,565 tok | p50 7,125 · p95 10,541 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_llama31_8b_v1 · rescored 77adc97b served on mac | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,565 tok | p50 7,125 · p95 10,541 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_llama31_8b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,565 tok | p50 7,125 · p95 10,541 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd served on x3 | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,490 tok | p50 5,389 · p95 8,370 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_llama31_8b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,490 tok | p50 5,389 · p95 8,370 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_llama31_8b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,490 tok | p50 5,389 · p95 8,370 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_llama31_8b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.415 ↓ | 65 | $0.000000 · 5,490 tok | p50 5,389 · p95 8,370 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v1 served on dgx | triage_cost | 0.477 ↓ | 65 | $0.000000 · 3,538 tok | p50 12,488 · p95 21,540 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.477 ↓ | 65 | $0.000000 · 3,538 tok | p50 12,488 · p95 21,540 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_escalate_v1 run on Linux/x86_64, 32 CPUs | triage_cost | 0.477 ↓ | 65 | 1,100 tok | p50 0.085 · p95 0.13 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_escalate_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.477 ↓ | 65 | 1,100 tok | p50 0.085 · p95 0.13 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_escalate_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.477 ↓ | 65 | 1,100 tok | p50 0.085 · p95 0.13 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_escalate_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.477 ↓ | 65 | 1,100 tok | p50 0.085 · p95 0.13 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_escalate_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.477 ↓ | 65 | 1,100 tok | p50 0.085 · p95 0.13 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v1 served on dgx | triage_cost | 0.523 ↓ | 65 | $0.000000 · 6,295 tok | p50 14,013 · p95 22,893 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.523 ↓ | 65 | $0.000000 · 6,295 tok | p50 14,013 · p95 22,893 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.523 ↓ | 65 | $0.000000 · 6,295 tok | p50 14,013 · p95 22,893 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.523 ↓ | 65 | $0.000000 · 6,295 tok | p50 14,013 · p95 22,893 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v1 served on x3 | triage_cost | 0.523 ↓ | 65 | $0.000000 · 7,352 tok | p50 33,430 · p95 80,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.523 ↓ | 65 | $0.000000 · 7,352 tok | p50 33,430 · p95 80,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.523 ↓ | 65 | $0.000000 · 7,352 tok | p50 33,430 · p95 80,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.523 ↓ | 65 | $0.000000 · 7,352 tok | p50 33,430 · p95 80,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.538 ↓ | 65 | $0.001368 · 3,125 tok | p50 3,353 · p95 5,695 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_35_flash_lite_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.538 ↓ | 65 | $0.001368 · 3,125 tok | p50 3,353 · p95 5,695 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_35_flash_lite_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.538 ↓ | 65 | $0.001368 · 3,125 tok | p50 3,353 · p95 5,695 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_35_flash_lite_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.538 ↓ | 65 | $0.001368 · 3,125 tok | p50 3,353 · p95 5,695 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.554 ↓ | 65 | $0.000668 · 5,346 tok | p50 8,324 · p95 11,239 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.554 ↓ | 65 | $0.000668 · 5,346 tok | p50 8,324 · p95 11,239 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.554 ↓ | 65 | $0.000668 · 5,346 tok | p50 8,324 · p95 11,239 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v1 served on mac | triage_cost | 0.554 ↓ | 65 | $0.000000 · 3,429 tok | p50 17,421 · p95 30,731 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.554 ↓ | 65 | $0.000000 · 3,429 tok | p50 17,421 · p95 30,731 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v2 served on x3 | triage_cost | 0.554 ↓ | 65 | $0.000000 · 5,306 tok | p50 5,534 · p95 7,717 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd served on x3 | triage_cost | 0.554 ↓ | 65 | $0.000000 · 5,306 tok | p50 5,534 · p95 7,717 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c served on x3 | triage_cost | 0.554 ↓ | 65 | $0.000000 · 5,306 tok | p50 5,534 · p95 7,717 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.010918 · 4,160 tok | p50 11,696 · p95 18,138 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.010918 · 4,160 tok | p50 11,696 · p95 18,138 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.010918 · 4,160 tok | p50 11,696 · p95 18,138 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.010918 · 4,160 tok | p50 11,696 · p95 18,138 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000715 · 4,764 tok | p50 11,518 · p95 21,428 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000715 · 4,764 tok | p50 11,518 · p95 21,428 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000715 · 4,764 tok | p50 11,518 · p95 21,428 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000998 · 5,684 tok | p50 6,867 · p95 13,887 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000998 · 5,684 tok | p50 6,867 · p95 13,887 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000998 · 5,684 tok | p50 6,867 · p95 13,887 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.585 ↓ | 65 | $0.000998 · 5,684 tok | p50 6,867 · p95 13,887 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_12b_noreason_v1 served on dgx | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,389 tok | p50 5,603 · p95 8,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd served on dgx | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,389 tok | p50 5,603 · p95 8,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,389 tok | p50 5,603 · p95 8,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b served on dgx | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,389 tok | p50 5,603 · p95 8,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,389 tok | p50 5,603 · p95 8,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_12b_noreason_v1 served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,311 tok | p50 8,599 · p95 13,904 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,311 tok | p50 8,599 · p95 13,904 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,311 tok | p50 8,599 · p95 13,904 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,311 tok | p50 8,599 · p95 13,904 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 3,311 tok | p50 8,599 · p95 13,904 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v2 served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 5,696 tok | p50 5,737 · p95 7,706 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 5,696 tok | p50 5,737 · p95 7,706 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c served on mac | triage_cost | 0.585 ↓ | 65 | $0.000000 · 5,696 tok | p50 5,737 · p95 7,706 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 21,363 · p95 33,502 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 20,275 · p95 32,697 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 21,363 · p95 33,502 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 20,275 · p95 32,697 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 21,363 · p95 33,502 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 20,275 · p95 32,697 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 21,363 · p95 33,502 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats served on x3 | triage_cost | 0.600 ↓ | 65 | $0.000000 · 6,171 tok | p50 20,275 · p95 32,697 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.610 ↓ | 65 | $0.001024 · 5,815 tok | p50 7,273 · p95 12,605 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.610 ↓ | 65 | $0.001024 · 5,815 tok | p50 7,273 · p95 12,605 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.610 ↓ | 65 | $0.001024 · 5,815 tok | p50 7,273 · p95 12,605 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.610 ↓ | 65 | $0.001024 · 5,815 tok | p50 7,273 · p95 12,605 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.626 ↓ | 65 | $0.000684 · 4,621 tok | p50 10,962 · p95 18,893 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.626 ↓ | 65 | $0.000684 · 4,621 tok | p50 10,962 · p95 18,893 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.626 ↓ | 65 | $0.000684 · 4,621 tok | p50 10,962 · p95 18,893 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.631 ↓ | 65 | $0.000627 · 3,330 tok | p50 6,448 · p95 11,349 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.631 ↓ | 65 | $0.000627 · 3,330 tok | p50 6,448 · p95 11,349 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.631 ↓ | 65 | $0.000627 · 3,330 tok | p50 6,448 · p95 11,349 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_4_argon_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.013617 · 4,751 tok | p50 23,508 · p95 61,827 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_4_argon_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.013617 · 4,751 tok | p50 23,508 · p95 61,827 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_4_argon_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.013617 · 4,751 tok | p50 23,508 · p95 61,827 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_4_argon_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.013617 · 4,751 tok | p50 23,508 · p95 61,827 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.019130 · 5,576 tok | p50 43,158 · p95 79,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.019130 · 5,576 tok | p50 43,158 · p95 79,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.646 ↓ | 65 | $0.019130 · 5,576 tok | p50 43,158 · p95 79,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v2 served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 5,506 tok | p50 3,850 · p95 5,195 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 5,506 tok | p50 3,850 · p95 5,195 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 5,506 tok | p50 3,850 · p95 5,195 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v1 served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,756 tok | p50 34,999 · p95 73,667 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,756 tok | p50 34,999 · p95 73,667 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,756 tok | p50 34,999 · p95 73,667 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,756 tok | p50 34,999 · p95 73,667 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v1 served on mac | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,484 tok | p50 55,843 · p95 129,188 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,484 tok | p50 55,843 · p95 129,188 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b served on mac | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,484 tok | p50 55,843 · p95 129,188 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.646 ↓ | 65 | $0.000000 · 7,484 tok | p50 55,843 · p95 129,188 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.662 ↓ | 65 | $0.010847 · 4,156 tok | p50 12,311 · p95 19,302 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.662 ↓ | 65 | $0.010847 · 4,156 tok | p50 12,311 · p95 19,302 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.662 ↓ | 65 | $0.010847 · 4,156 tok | p50 12,311 · p95 19,302 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.662 ↓ | 65 | $0.010847 · 4,156 tok | p50 12,311 · p95 19,302 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v2 served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 3,135 tok | p50 7,719 · p95 10,098 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 3,135 tok | p50 7,719 · p95 10,098 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 3,135 tok | p50 7,719 · p95 10,098 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_phi4_14b_v1 served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 6,064 tok | p50 17,140 · p95 23,284 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 6,064 tok | p50 17,140 · p95 23,284 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 6,064 tok | p50 17,140 · p95 23,284 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_phi4_14b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 6,064 tok | p50 17,140 · p95 23,284 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.662 ↓ | 65 | $0.000000 · 6,064 tok | p50 17,140 · p95 23,284 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.677 ↓ | 65 | $0.000849 · 3,854 tok | p50 16,361 · p95 31,807 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.677 ↓ | 65 | $0.000849 · 3,854 tok | p50 16,361 · p95 31,807 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.677 ↓ | 65 | $0.000849 · 3,854 tok | p50 16,361 · p95 31,807 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v1 served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,384 tok | p50 46,681 · p95 127,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,384 tok | p50 46,681 · p95 127,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,384 tok | p50 46,681 · p95 127,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,384 tok | p50 46,681 · p95 127,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v2 served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 6,286 tok | p50 6,762 · p95 8,238 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 6,286 tok | p50 6,762 · p95 8,238 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 6,286 tok | p50 6,762 · p95 8,238 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v1 served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 4,514 tok | p50 36,513 · p95 70,263 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 4,514 tok | p50 36,513 · p95 70,263 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 4,514 tok | p50 36,513 · p95 70,263 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 4,514 tok | p50 36,513 · p95 70,263 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v2 served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,246 tok | p50 15,795 · p95 21,883 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,246 tok | p50 15,795 · p95 21,883 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c served on dgx | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,246 tok | p50 15,795 · p95 21,883 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v1 served on mac | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,271 tok | p50 91,096 · p95 182,205 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,271 tok | p50 91,096 · p95 182,205 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v1 · rescored 77adc97b served on mac | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,271 tok | p50 91,096 · p95 182,205 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.677 ↓ | 65 | $0.000000 · 5,271 tok | p50 91,096 · p95 182,205 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v2 served on x3 | triage_cost | 0.677 ↓ | 65 | $0.000000 · 6,288 tok | p50 7,933 · p95 9,459 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd served on x3 | triage_cost | 0.677 ↓ | 65 | $0.000000 · 6,288 tok | p50 7,933 · p95 9,459 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c served on x3 | triage_cost | 0.677 ↓ | 65 | $0.000000 · 6,288 tok | p50 7,933 · p95 9,459 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v1 served on dgx | triage_cost | 0.692 ↓ | 65 | $0.000000 · 3,194 tok | p50 13,206 · p95 24,077 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.692 ↓ | 65 | $0.000000 · 3,194 tok | p50 13,206 · p95 24,077 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.692 ↓ | 65 | $0.000000 · 3,194 tok | p50 13,206 · p95 24,077 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.692 ↓ | 65 | $0.000000 · 3,194 tok | p50 13,206 · p95 24,077 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v2 served on mac | triage_cost | 0.692 ↓ | 65 | $0.000000 · 6,265 tok | p50 11,237 · p95 14,132 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd served on mac | triage_cost | 0.692 ↓ | 65 | $0.000000 · 6,265 tok | p50 11,237 · p95 14,132 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c served on mac | triage_cost | 0.692 ↓ | 65 | $0.000000 · 6,265 tok | p50 11,237 · p95 14,132 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v1 served on x3 | triage_cost | 0.692 ↓ | 65 | $0.000000 · 5,386 tok | p50 60,463 · p95 159,924 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.692 ↓ | 65 | $0.000000 · 5,386 tok | p50 60,463 · p95 159,924 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.692 ↓ | 65 | $0.000000 · 5,386 tok | p50 60,463 · p95 159,924 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.692 ↓ | 65 | $0.000000 · 5,386 tok | p50 60,463 · p95 159,924 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen3_30b_a3b_v1 run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.000700 · 6,111 tok | p50 16,982 · p95 35,517 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.000700 · 6,111 tok | p50 16,982 · p95 35,517 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.000700 · 6,111 tok | p50 16,982 · p95 35,517 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.000700 · 6,111 tok | p50 16,982 · p95 35,517 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.000700 · 6,111 tok | p50 16,982 · p95 35,517 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v2 served on mac | triage_cost | 0.708 ↓ | 65 | $0.000000 · 3,270 tok | p50 5,856 · p95 8,006 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd served on mac | triage_cost | 0.708 ↓ | 65 | $0.000000 · 3,270 tok | p50 5,856 · p95 8,006 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c served on mac | triage_cost | 0.708 ↓ | 65 | $0.000000 · 3,270 tok | p50 5,856 · p95 8,006 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v2 served on x3 | triage_cost | 0.708 ↓ | 65 | $0.000000 · 4,219 tok | p50 14,550 · p95 21,031 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd served on x3 | triage_cost | 0.708 ↓ | 65 | $0.000000 · 4,219 tok | p50 14,550 · p95 21,031 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c served on x3 | triage_cost | 0.708 ↓ | 65 | $0.000000 · 4,219 tok | p50 14,550 · p95 21,031 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_sonnet_55_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.022659 · 7,149 tok | p50 12,111 · p95 20,225 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_sonnet_55_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.022659 · 7,149 tok | p50 12,111 · p95 20,225 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_sonnet_55_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.022659 · 7,149 tok | p50 12,111 · p95 20,225 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_sonnet_55_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.708 ↓ | 65 | $0.022659 · 7,149 tok | p50 12,111 · p95 20,225 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.723 ↓ | 65 | $0.000903 · 4,276 tok | p50 9,818 · p95 19,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.723 ↓ | 65 | $0.000903 · 4,276 tok | p50 9,818 · p95 19,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.723 ↓ | 65 | $0.000903 · 4,276 tok | p50 9,818 · p95 19,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.723 ↓ | 65 | $0.000897 · 4,242 tok | p50 6,789 · p95 32,394 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.723 ↓ | 65 | $0.000897 · 4,242 tok | p50 6,789 · p95 32,394 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.723 ↓ | 65 | $0.000897 · 4,242 tok | p50 6,789 · p95 32,394 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.723 ↓ | 65 | $0.012041 · 4,605 tok | p50 22,561 · p95 34,524 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.723 ↓ | 65 | $0.012041 · 4,605 tok | p50 22,561 · p95 34,524 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.723 ↓ | 65 | $0.012041 · 4,605 tok | p50 22,561 · p95 34,524 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v2 served on dgx | triage_cost | 0.723 ↓ | 65 | $0.000000 · 4,333 tok | p50 12,714 · p95 18,314 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 0.723 ↓ | 65 | $0.000000 · 4,333 tok | p50 12,714 · p95 18,314 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c served on dgx | triage_cost | 0.723 ↓ | 65 | $0.000000 · 4,333 tok | p50 12,714 · p95 18,314 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v2 served on dgx | triage_cost | 0.723 ↓ | 65 | $0.000000 · 2,977 tok | p50 4,298 · p95 6,526 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 0.723 ↓ | 65 | $0.000000 · 2,977 tok | p50 4,298 · p95 6,526 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c served on dgx | triage_cost | 0.723 ↓ | 65 | $0.000000 · 2,977 tok | p50 4,298 · p95 6,526 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen3_30b_a3b_v1 served on x3 | triage_cost | 0.723 ↓ | 65 | $0.000000 · 6,231 tok | p50 6,349 · p95 10,328 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd served on x3 | triage_cost | 0.723 ↓ | 65 | $0.000000 · 6,231 tok | p50 6,349 · p95 10,328 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.723 ↓ | 65 | $0.000000 · 6,231 tok | p50 6,349 · p95 10,328 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.723 ↓ | 65 | $0.000000 · 6,231 tok | p50 6,349 · p95 10,328 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.723 ↓ | 65 | $0.000000 · 6,231 tok | p50 6,349 · p95 10,328 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.754 ↓ | 65 | $0.000862 · 5,180 tok | p50 6,905 · p95 27,865 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.754 ↓ | 65 | $0.000862 · 5,180 tok | p50 6,905 · p95 27,865 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.754 ↓ | 65 | $0.000862 · 5,180 tok | p50 6,905 · p95 27,865 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v1 served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 6,321 tok | p50 21,874 · p95 33,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 6,321 tok | p50 21,874 · p95 33,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 6,321 tok | p50 21,874 · p95 33,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 6,321 tok | p50 21,874 · p95 33,411 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_phi4_14b_v1 served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 5,888 tok | p50 22,493 · p95 27,539 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 5,888 tok | p50 22,493 · p95 27,539 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_phi4_14b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 5,888 tok | p50 22,493 · p95 27,539 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_phi4_14b_v1 · rescored 77adc97b served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 5,888 tok | p50 22,493 · p95 27,539 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_phi4_14b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.754 ↓ | 65 | $0.000000 · 5,888 tok | p50 22,493 · p95 27,539 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.764 ↓ | 65 | $0.005104 · 4,916 tok | p50 21,498 · p95 55,678 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.764 ↓ | 65 | $0.005104 · 4,916 tok | p50 21,498 · p95 55,678 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.764 ↓ | 65 | $0.005104 · 4,916 tok | p50 21,498 · p95 55,678 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 run on Linux/x86_64, 32 CPUs | triage_cost | 0.764 ↓ | 65 | $0.005104 · 4,916 tok | p50 21,498 · p95 55,678 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_phi4_14b_v1 served on x3 | triage_cost | 0.769 ↓ | 65 | $0.000000 · 5,949 tok | p50 16,420 · p95 21,153 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd served on x3 | triage_cost | 0.769 ↓ | 65 | $0.000000 · 5,949 tok | p50 16,420 · p95 21,153 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_phi4_14b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.769 ↓ | 65 | $0.000000 · 5,949 tok | p50 16,420 · p95 21,153 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_phi4_14b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.769 ↓ | 65 | $0.000000 · 5,949 tok | p50 16,420 · p95 21,153 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_phi4_14b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.769 ↓ | 65 | $0.000000 · 5,949 tok | p50 16,420 · p95 21,153 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.785 ↓ | 65 | $0.004992 · 4,790 tok | p50 19,965 · p95 47,741 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored 5f2c057c baseline run on Linux/x86_64, 32 CPUs | triage_cost | 0.785 ↓ | 65 | $0.004992 · 4,790 tok | p50 19,965 · p95 47,741 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.785 ↓ | 65 | $0.004992 · 4,790 tok | p50 19,965 · p95 47,741 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.785 ↓ | 65 | $0.004992 · 4,790 tok | p50 19,965 · p95 47,741 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v2 served on mac | triage_cost | 0.800 ↓ | 65 | $0.000000 · 4,345 tok | p50 24,585 · p95 36,311 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd served on mac | triage_cost | 0.800 ↓ | 65 | $0.000000 · 4,345 tok | p50 24,585 · p95 36,311 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c served on mac | triage_cost | 0.800 ↓ | 65 | $0.000000 · 4,345 tok | p50 24,585 · p95 36,311 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.800 ↓ | 65 | $0.006867 · 6,704 tok | p50 15,459 · p95 30,084 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.800 ↓ | 65 | $0.006867 · 6,704 tok | p50 15,459 · p95 30,084 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.800 ↓ | 65 | $0.006867 · 6,704 tok | p50 15,459 · p95 30,084 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.800 ↓ | 65 | $0.006948 · 6,760 tok | p50 19,158 · p95 35,678 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.800 ↓ | 65 | $0.006948 · 6,760 tok | p50 19,158 · p95 35,678 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.800 ↓ | 65 | $0.006948 · 6,760 tok | p50 19,158 · p95 35,678 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v2 served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 3,225 tok | p50 6,092 · p95 8,461 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 3,225 tok | p50 6,092 · p95 8,461 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 3,225 tok | p50 6,092 · p95 8,461 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_ministral_3_14b_v1 served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 6,617 tok | p50 22,275 · p95 31,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 6,617 tok | p50 22,275 · p95 31,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 6,617 tok | p50 22,275 · p95 31,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 6,617 tok | p50 22,275 · p95 31,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.815 ↓ | 65 | $0.000000 · 6,617 tok | p50 22,275 · p95 31,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_ministral_3_14b_v1 served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,489 tok | p50 19,704 · p95 29,658 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,489 tok | p50 19,704 · p95 29,658 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,489 tok | p50 19,704 · p95 29,658 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,489 tok | p50 19,704 · p95 29,658 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,489 tok | p50 19,704 · p95 29,658 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v1 served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 4,536 tok | p50 33,735 · p95 60,085 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 4,536 tok | p50 33,735 · p95 60,085 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 4,536 tok | p50 33,735 · p95 60,085 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.831 ↓ | 65 | $0.000000 · 4,536 tok | p50 33,735 · p95 60,085 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_ministral_3_14b_v1 served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,497 tok | p50 27,548 · p95 39,331 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,497 tok | p50 27,548 · p95 39,331 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen3_30b_a3b_v1 served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,279 tok | p50 8,898 · p95 13,952 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,279 tok | p50 8,898 · p95 13,952 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,279 tok | p50 8,898 · p95 13,952 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,279 tok | p50 8,898 · p95 13,952 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f served on mac | triage_cost | 0.831 ↓ | 65 | $0.000000 · 6,279 tok | p50 8,898 · p95 13,952 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_dismiss_v1 run on Linux/x86_64, 32 CPUs | triage_cost | 0.862 ↓ | 65 | 1,100 tok | p50 0.092 · p95 0.17 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_dismiss_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.862 ↓ | 65 | 1,100 tok | p50 0.092 · p95 0.17 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_dismiss_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.862 ↓ | 65 | 1,100 tok | p50 0.092 · p95 0.17 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_dismiss_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.862 ↓ | 65 | 1,100 tok | p50 0.092 · p95 0.17 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_stub_dismiss_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.862 ↓ | 65 | 1,100 tok | p50 0.092 · p95 0.17 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd run on Linux/x86_64, 32 CPUs | triage_cost | 0.877 ↓ | 65 | $0.011539 · 6,292 tok | p50 6,080 · p95 8,340 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 0.877 ↓ | 65 | $0.011539 · 6,292 tok | p50 6,080 · p95 8,340 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_mistral_medium_35_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 0.877 ↓ | 65 | $0.011539 · 6,292 tok | p50 6,080 · p95 8,340 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 0.877 ↓ | 65 | $0.011539 · 6,292 tok | p50 6,080 · p95 8,340 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.877 ↓ | 65 | $0.001654 · 4,247 tok | p50 6,774 · p95 9,273 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.877 ↓ | 65 | $0.001654 · 4,247 tok | p50 6,774 · p95 9,273 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.877 ↓ | 65 | $0.001654 · 4,247 tok | p50 6,774 · p95 9,273 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen3_30b_a3b_v1 served on dgx | triage_cost | 0.892 ↓ | 65 | $0.000000 · 6,384 tok | p50 5,362 · p95 8,443 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd served on dgx | triage_cost | 0.892 ↓ | 65 | $0.000000 · 6,384 tok | p50 5,362 · p95 8,443 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c served on dgx | triage_cost | 0.892 ↓ | 65 | $0.000000 · 6,384 tok | p50 5,362 · p95 8,443 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b served on dgx | triage_cost | 0.892 ↓ | 65 | $0.000000 · 6,384 tok | p50 5,362 · p95 8,443 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f served on dgx | triage_cost | 0.892 ↓ | 65 | $0.000000 · 6,384 tok | p50 5,362 · p95 8,443 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v2 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.908 ↓ | 65 | $0.000355 · 4,756 tok | p50 2,897 · p95 6,148 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v2 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.908 ↓ | 65 | $0.000355 · 4,756 tok | p50 2,897 · p95 6,148 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v2 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 0.908 ↓ | 65 | $0.000355 · 4,756 tok | p50 2,897 · p95 6,148 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd served on mac | triage_cost | 0.908 ↓ | 65 | $0.000000 · 6,497 tok | p50 27,548 · p95 39,331 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c served on mac | triage_cost | 0.908 ↓ | 65 | $0.000000 · 6,497 tok | p50 27,548 · p95 39,331 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b served on mac | triage_cost | 0.908 ↓ | 65 | $0.000000 · 6,497 tok | p50 27,548 · p95 39,331 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v1 served on x3 | triage_cost | 0.908 ↓ | 65 | $0.000000 · 4,388 tok | p50 43,283 · p95 76,811 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c served on x3 | triage_cost | 0.908 ↓ | 65 | $0.000000 · 4,388 tok | p50 43,283 · p95 76,811 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v1 · rescored 77adc97b served on x3 | triage_cost | 0.908 ↓ | 65 | $0.000000 · 4,388 tok | p50 43,283 · p95 76,811 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f served on x3 | triage_cost | 0.908 ↓ | 65 | $0.000000 · 4,388 tok | p50 43,283 · p95 76,811 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_mistral_medium_35_128b_v1 served on dgx | triage_cost | 1.000 ↓ | 65 | $0.000000 · 5,941 tok | p50 112,303 · p95 167,929 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd served on dgx | triage_cost | 1.000 ↓ | 65 | $0.000000 · 5,941 tok | p50 112,303 · p95 167,929 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c served on dgx | triage_cost | 1.000 ↓ | 65 | $0.000000 · 5,941 tok | p50 112,303 · p95 167,929 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b served on dgx | triage_cost | 1.000 ↓ | 65 | $0.000000 · 5,941 tok | p50 112,303 · p95 167,929 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f served on dgx | triage_cost | 1.000 ↓ | 65 | $0.000000 · 5,941 tok | p50 112,303 · p95 167,929 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c served on dgx | triage_cost | 1.015 ↓ | 65 | $0.000000 · 3,538 tok | p50 12,488 · p95 21,540 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b served on dgx | triage_cost | 1.015 ↓ | 65 | $0.000000 · 3,538 tok | p50 12,488 · p95 21,540 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v1 served on mac | triage_cost | 1.046 ↓ | 65 | $0.000000 · 4,483 tok | p50 62,523 · p95 121,029 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c served on mac | triage_cost | 1.046 ↓ | 65 | $0.000000 · 4,483 tok | p50 62,523 · p95 121,029 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v1 · rescored 77adc97b served on mac | triage_cost | 1.046 ↓ | 65 | $0.000000 · 4,483 tok | p50 62,523 · p95 121,029 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f served on mac | triage_cost | 1.046 ↓ | 65 | $0.000000 · 4,483 tok | p50 62,523 · p95 121,029 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v1 · rescored 5f2c057c run on Linux/x86_64, 32 CPUs | triage_cost | 1.077 ↓ | 65 | $0.003350 · 5,474 tok | p50 15,600 · p95 33,509 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v1 · rescored 77adc97b run on Linux/x86_64, 32 CPUs | triage_cost | 1.077 ↓ | 65 | $0.003350 · 5,474 tok | p50 15,600 · p95 33,509 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v1 · rescored cd35dc1f run on Linux/x86_64, 32 CPUs | triage_cost | 1.077 ↓ | 65 | $0.003350 · 5,474 tok | p50 15,600 · p95 33,509 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c served on mac | triage_cost | 1.092 ↓ | 65 | $0.000000 · 3,429 tok | p50 17,421 · p95 30,731 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b served on mac | triage_cost | 1.092 ↓ | 65 | $0.000000 · 3,429 tok | p50 17,421 · p95 30,731 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c served on x3 | triage_cost | 1.092 ↓ | 65 | $0.000000 · 3,619 tok | p50 16,207 · p95 29,798 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b served on x3 | triage_cost | 1.092 ↓ | 65 | $0.000000 · 3,619 tok | p50 16,207 · p95 29,798 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v1 served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 5,318 tok | p50 35,972 · p95 57,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 5,318 tok | p50 35,972 · p95 57,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 5,318 tok | p50 35,972 · p95 57,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 5,318 tok | p50 35,972 · p95 57,784 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v2 served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 4,585 tok | p50 15,771 · p95 24,424 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 4,585 tok | p50 15,771 · p95 24,424 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c served on dgx | triage_cost | 1.138 ↓ | 65 | $0.000000 · 4,585 tok | p50 15,771 · p95 24,424 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v2 served on mac | triage_cost | 1.138 ↓ | 65 | $0.000000 · 4,569 tok | p50 32,196 · p95 46,026 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd served on mac | triage_cost | 1.138 ↓ | 65 | $0.000000 · 4,569 tok | p50 32,196 · p95 46,026 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c served on mac | triage_cost | 1.138 ↓ | 65 | $0.000000 · 4,569 tok | p50 32,196 · p95 46,026 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_noreason_v1 served on homelab LiteLLM (the fleet's gateway) | triage_cost | 1.154 ↓ | 65 | $0.004862 · 5,590 tok | p50 7,710 · p95 14,703 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_noreason_v1 · rescored 3d3a6afd served on homelab LiteLLM (the fleet's gateway) | triage_cost | 1.154 ↓ | 65 | $0.004862 · 5,590 tok | p50 7,710 · p95 14,703 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_noreason_v1 · rescored 5f2c057c served on homelab LiteLLM (the fleet's gateway) | triage_cost | 1.154 ↓ | 65 | $0.004862 · 5,590 tok | p50 7,710 · p95 14,703 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama4_scout_v1 served on dgx | triage_cost | 1.262 ↓ | 65 | $0.000000 · 5,629 tok | p50 13,116 · p95 17,645 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd served on dgx | triage_cost | 1.262 ↓ | 65 | $0.000000 · 5,629 tok | p50 13,116 · p95 17,645 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c served on dgx | triage_cost | 1.262 ↓ | 65 | $0.000000 · 5,629 tok | p50 13,116 · p95 17,645 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama4_scout_v1 · rescored 77adc97b served on dgx | triage_cost | 1.262 ↓ | 65 | $0.000000 · 5,629 tok | p50 13,116 · p95 17,645 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f served on dgx | triage_cost | 1.262 ↓ | 65 | $0.000000 · 5,629 tok | p50 13,116 · p95 17,645 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v2 served on x3 | triage_cost | 1.292 ↓ | 65 | $0.000000 · 4,523 tok | p50 19,431 · p95 31,568 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd served on x3 | triage_cost | 1.292 ↓ | 65 | $0.000000 · 4,523 tok | p50 19,431 · p95 31,568 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c served on x3 | triage_cost | 1.292 ↓ | 65 | $0.000000 · 4,523 tok | p50 19,431 · p95 31,568 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v2 served on dgx | triage_cost | 1.354 ↓ | 65 | $0.000000 · 4,180 tok | p50 15,011 · p95 19,803 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd served on dgx | triage_cost | 1.354 ↓ | 65 | $0.000000 · 4,180 tok | p50 15,011 · p95 19,803 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c served on dgx | triage_cost | 1.354 ↓ | 65 | $0.000000 · 4,180 tok | p50 15,011 · p95 19,803 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_local_x3_llama31_8b_v1 served on x3 | false_dismiss | 0.000 ↓ | 34 | $0.000000 · 5,490 tok | p50 5,389 · p95 8,370 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_35_flash_lite_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.088 ↓ | 34 | $0.001368 · 3,125 tok | p50 3,353 · p95 5,695 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 · repeats ×3 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.088 ↓ | 34 | $0.010918 · 4,160 tok | p50 11,696 · p95 18,138 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.088 ↓ | 34 | $0.000715 · 4,764 tok | p50 11,518 · p95 21,428 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gemini_4_argon_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.118 ↓ | 34 | $0.013617 · 4,751 tok | p50 23,508 · p95 61,827 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_61_sol_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.118 ↓ | 34 | $0.010847 · 4,156 tok | p50 12,311 · p95 19,302 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_gpt_6_luna_v1 · repeats ×3 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.118 ↓ | 34 | $0.000684 · 4,621 tok | p50 10,962 · p95 18,893 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.118 ↓ | 34 | $0.000998 · 5,684 tok | p50 6,867 · p95 13,887 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_haiku_55_v1 · repeats ×3 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.118 ↓ | 34 | $0.001024 · 5,815 tok | p50 7,273 · p95 12,605 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_kimi_k31_pro_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.118 ↓ | 34 | $0.019130 · 5,576 tok | p50 43,158 · p95 79,162 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gpt_oss_120b_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.147 ↓ | 34 | $0.000849 · 3,854 tok | p50 16,361 · p95 31,807 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_sonnet_55_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.147 ↓ | 34 | $0.022659 · 7,149 tok | p50 12,111 · p95 20,225 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 · repeats ×3 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.167 ↓ | 34 | $0.005104 · 4,916 tok | p50 21,498 · p95 55,678 ms | 3 | gold/orrery_triage_v1_labelled gold | inspect |
triage_baseline_pro_v1 baseline run on Linux/x86_64, 32 CPUs | false_dismiss | 0.176 ↓ | 34 | $0.004992 · 4,790 tok | p50 19,965 · p95 47,741 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_deepseek_41flash_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.176 ↓ | 34 | $0.000862 · 5,180 tok | p50 6,905 · p95 27,865 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_gemma4_31b_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.176 ↓ | 34 | $0.000903 · 4,276 tok | p50 9,818 · p95 19,215 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_mistral_large_4_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.176 ↓ | 34 | $0.006867 · 6,704 tok | p50 15,459 · p95 30,084 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_mistral_medium_35_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.235 ↓ | 34 | $0.011539 · 6,292 tok | p50 6,080 · p95 8,340 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |
triage_hosted_qwen35_122b_v1 run on Linux/x86_64, 32 CPUs | false_dismiss | 0.294 ↓ | 34 | $0.003350 · 5,474 tok | p50 15,600 · p95 33,509 ms | 1 | gold/orrery_triage_v1_labelled gold | inspect |