cohort,id,name,provider,campaign,reasoning,endpoint_revision,output_cap,advertised_context_tokens,observed_prompt_tokens_min,observed_prompt_tokens_max,prompt_usage_records,dispatched_calls,label_matches,assigned_labels,complete_calls,assigned_calls,known_usd,median_seconds,classified_labels,missing_labels,disagreements,agreement_received,classification_coverage,all_calls_complete,accounting_complete,evidence_url internal,reflection/beam-1.0-501b-a23b,Reflection: Beam 1.0 501B A23B,nebius/fp4,internal-expansion-2026-11-11,high,Nebius | reflection/beam-1.0-501b-a23b-20261016,32768,1048576,378,1327,18,18,324,324,18,18,0.0469119,3.4604492914950242,324,0,0,1.0,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,anthropic/claude-opus-5.5,Anthropic: Claude Opus 5.5,anthropic,internal-frontier-2026-11-11,high,Anthropic | anthropic/claude-opus-5.5-20260921,32768,1000000,521,2045,18,18,322,324,18,18,0.361496,6.458620729004906,324,0,2,0.9938271604938271,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/c85624939bde546d67f3869c656cfb8b97b7ae00/internal_tests/2026-11-11-frontier internal,cohere/command-a-plus,Cohere: Command A+,cohere/fp8,internal-expansion-2026-11-11,enabled,Cohere | cohere/command-a-plus-05-2026,32768,192000,305,1154,18,18,324,324,17,18,0.133929,10.535405374495895,324,0,0,1.0,1.0,False,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,deepseek/deepseek-v4.1-flash-1017,DeepSeek: DeepSeek V4.1 Flash 1017,relace/fp4,internal-expansion-2026-11-11,high,Relace | deepseek/deepseek-v4.1-flash-20261017,32768,1048576,339,1210,18,18,288,324,18,18,0.012894476,9.657867458496185,288,36,0,1.0,0.8888888888888888,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,baidu/ernie-5.5-flash-preview,Baidu: ERNIE-5.5-Flash-Preview,baidu,internal-expansion-2026-11-11,high,Baidu | baidu/ernie-5.5-flash-preview-20261110,32768,1024000,335,1197,17,18,321,324,17,18,0.054967776,4.406672417004302,324,0,3,0.9907407407407407,1.0,False,False,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,sakana/fugu-max,Sakana: Fugu Max,sakana,internal-legacy-extension-2026-11-11,high,Sakana AI | sakana/fugu-max-20260911,32768,1000000,,,0,0,0,324,0,18,0.0,,0,324,0,,0.0,False,False,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-legacy-extension internal,google/gemini-4-argon,Google: Gemini 4 Argon,google-ai-studio,internal-frontier-2026-11-11,high,Google AI Studio | google/gemini-4-argon-20261013,32768,1048576,375,1521,17,18,288,324,17,18,0.365732,21.948203687505156,288,36,0,1.0,0.8888888888888888,False,False,https://github.com/sev7enITA/PALO-BlueprintBench/tree/c85624939bde546d67f3869c656cfb8b97b7ae00/internal_tests/2026-11-11-frontier internal,z-ai/glm-5.3,Z.ai: GLM 5.3,wafer/us,internal-expansion-2026-11-11,high,Wafer | z-ai/glm-5.3-20260816,32768,1048576,321,1207,18,18,324,324,18,18,0.0364313253,14.445387541498349,324,0,0,1.0,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,openai/gpt-6.1-sol,OpenAI: GPT-6.1 Sol,openai,internal-frontier-2026-11-11,high,OpenAI | openai/gpt-6.1-sol-20260929,32768,1050000,319,1231,18,18,324,324,18,18,0.1033389,6.657791333003843,324,0,0,1.0,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/c85624939bde546d67f3869c656cfb8b97b7ae00/internal_tests/2026-11-11-frontier internal,tencent/hy4,Tencent: Hy4,tencent/fp4,internal-expansion-2026-11-11,high,Tencent | tencent/hy4-20261104,32768,1048576,330,1201,18,18,321,324,18,18,0.3030276935,118.15865729150391,324,0,3,0.9907407407407407,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,mistralai/mistral-large-4-0,Mistral: Mistral Large 4,mistral/zdr,internal-expansion-2026-11-11,high,Mistral | mistralai/mistral-large-4-0-20261006,32768,1048576,329,1303,18,18,315,324,18,18,0.18685044,24.570694166992325,324,0,9,0.9722222222222222,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,nex-agi/nex-n2.6,Nex AGI: Nex-N2.6,nex-agi/fp8,internal-expansion-2026-11-11,high,Nex AGI | nex-agi/nex-n2.6-20261110,32768,262144,321,1207,18,18,323,324,18,18,0.00945436,11.18205852099345,324,0,1,0.9969135802469136,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,qwen/qwen3.8-max-prime,Qwen: Qwen3.8 Max Prime,alibaba,internal-expansion-2026-11-11,high,Alibaba | qwen/qwen3.8-max-prime-20260923,32768,1000000,389,1329,18,18,322,324,18,18,0.658176,26.277907167001104,324,0,2,0.9938271604938271,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,inference-net/schematron-v2-small,Inference.net: Schematron V2 Small,inference-net/us,internal-legacy-extension-2026-11-11,not configured,InferenceNet | inference-net/schematron-v2-small-20260902,8192,128000,343,1197,18,18,62,324,17,18,0.00495931,1.1700871244975133,196,128,134,0.3163265306122449,0.6049382716049383,False,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-legacy-extension internal,inference-net/schematron-v2-turbo,Inference.net: Schematron V2 Turbo,inference-net/us,internal-expansion-2026-11-11,not configured,InferenceNet | inference-net/schematron-v2-turbo-20260902,8192,128000,335,1180,18,18,47,324,18,18,0.00146637,2.0725631459936267,149,175,102,0.31543624161073824,0.45987654320987653,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,upstage/solar-mini4,Upstage: Solar Mini 4,upstage/zdr,internal-expansion-2026-11-11,high,Upstage | upstage/solar-mini4-20260922,32768,524288,382,1320,18,18,324,324,18,18,0.01259505,55.41354081300233,324,0,0,1.0,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,prism-ml/ternary-bonsai-2-27b,PrismML: Ternary Bonsai 2 27B,darkbloom/int4,internal-expansion-2026-11-11,xhigh,Darkbloom | prism-ml/ternary-bonsai-2-27b-20260918,32768,262144,389,1455,15,18,216,324,15,18,0.0215451,50.366164500002924,216,108,0,1.0,0.6666666666666666,False,False,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-expansion internal,prism-ml/ternary-bonsai-2-9b,PrismML: Ternary Bonsai 2 9B,darkbloom/int4,internal-legacy-extension-2026-11-11,enabled,Darkbloom | prism-ml/ternary-bonsai-2-9b-20261015,32768,262144,351,1417,18,18,324,324,18,18,0.0098111,33.54686175000097,324,0,0,1.0,1.0,True,True,https://github.com/sev7enITA/PALO-BlueprintBench/tree/2b054692baea4ca1a892e3d39453a76097a64f74/internal_tests/2026-11-11-legacy-extension