https://ultrabench.ai/decision2026-10-23 https://ultrabench.ai/decision/benchmarks2026-10-23 https://ultrabench.ai/decision/benchmarks/decision_bench_accuracy https://ultrabench.ai/decision/benchmarks/decision_bench_ece https://ultrabench.ai/decision/benchmarks/decision_bench_nll https://ultrabench.ai/decision/benchmarks/decision_index_area_arts https://ultrabench.ai/decision/benchmarks/decision_index_area_knowledge https://ultrabench.ai/decision/benchmarks/decision_index_area_language https://ultrabench.ai/decision/benchmarks/decision_index_area_retrieval https://ultrabench.ai/decision/benchmarks/decision_index_area_tools https://ultrabench.ai/decision/benchmarks/decision_index_bm_amazon_esci https://ultrabench.ai/decision/benchmarks/decision_index_bm_anli https://ultrabench.ai/decision/benchmarks/decision_index_bm_apibank https://ultrabench.ai/decision/benchmarks/decision_index_bm_banking77 https://ultrabench.ai/decision/benchmarks/decision_index_bm_bbh https://ultrabench.ai/decision/benchmarks/decision_index_bm_bfcl https://ultrabench.ai/decision/benchmarks/decision_index_bm_bpomp https://ultrabench.ai/decision/benchmarks/decision_index_bm_bright https://ultrabench.ai/decision/benchmarks/decision_index_bm_clinc150 https://ultrabench.ai/decision/benchmarks/decision_index_bm_contractnli https://ultrabench.ai/decision/benchmarks/decision_index_bm_gpqa https://ultrabench.ai/decision/benchmarks/decision_index_bm_gsm8k https://ultrabench.ai/decision/benchmarks/decision_index_bm_hellaswag https://ultrabench.ai/decision/benchmarks/decision_index_bm_hle https://ultrabench.ai/decision/benchmarks/decision_index_bm_home_appliance https://ultrabench.ai/decision/benchmarks/decision_index_bm_humicroedit https://ultrabench.ai/decision/benchmarks/decision_index_bm_isarcasm https://ultrabench.ai/decision/benchmarks/decision_index_bm_mmlu_pro https://ultrabench.ai/decision/benchmarks/decision_index_bm_nli4ct https://ultrabench.ai/decision/benchmarks/decision_index_bm_toolret https://ultrabench.ai/decision/benchmarks/decision_index_bm_when2call https://ultrabench.ai/decision/benchmarks/decision_index_bm_winogrande https://ultrabench.ai/decision/benchmarks/decision_index_calib_accuracy https://ultrabench.ai/decision/benchmarks/decision_index_calib_brier https://ultrabench.ai/decision/benchmarks/decision_index_calib_ece https://ultrabench.ai/decision/benchmarks/decision_index_full https://ultrabench.ai/decision/benchmarks/decision_index_public https://ultrabench.ai/decision/benchmarks/decision_jevbench_calibration https://ultrabench.ai/decision/benchmarks/decision_jevbench_capability https://ultrabench.ai/decision/benchmarks/decision_jevbench_composite https://ultrabench.ai/decision/benchmarks/decision_jevbench_cost https://ultrabench.ai/decision/benchmarks/decision_jevbench_intelligence https://ultrabench.ai/decision/benchmarks/decision_jevbench_public_accuracy https://ultrabench.ai/decision/benchmarks/decision_jevbench_public_brier https://ultrabench.ai/decision/benchmarks/decision_jevbench_public_ece https://ultrabench.ai/decision/benchmarks/decision_jevbench_speed https://ultrabench.ai/decision/benchmarks/decision_s1bench https://ultrabench.ai/decision/benchmarks/decision_typesafe_workflow https://ultrabench.ai/decision/models/adata-decision-1-9b2026-10-14 https://ultrabench.ai/decision/models/avrik-lite-4b2026-10-14 https://ultrabench.ai/decision/models/avrik-pro-12b2026-10-14 https://ultrabench.ai/decision/models/bobcat-1-32026-10-14 https://ultrabench.ai/decision/models/bobcat-flash-1-22026-10-14 https://ultrabench.ai/decision/models/celeris-1-decision2026-10-14 https://ultrabench.ai/decision/models/clef2026-10-14 https://ultrabench.ai/decision/models/clef-flash2026-10-14 https://ultrabench.ai/decision/models/clef-omni2026-10-14 https://ultrabench.ai/decision/models/coco-decision-4b2026-10-14 https://ultrabench.ai/decision/models/coco-decision-4b-ko2026-10-14 https://ultrabench.ai/decision/models/cua-s1-4b-0-22026-10-14 https://ultrabench.ai/decision/models/cua-s1-forms2026-10-14 https://ultrabench.ai/decision/models/d12026-10-14 https://ultrabench.ai/decision/models/d1-3b2026-10-14 https://ultrabench.ai/decision/models/d1-omni-600m2026-10-14 https://ultrabench.ai/decision/models/d32026-10-14 https://ultrabench.ai/decision/models/d3-edge2026-10-14 https://ultrabench.ai/decision/models/d3-flash2026-10-14 https://ultrabench.ai/decision/models/d3-lite2026-10-14 https://ultrabench.ai/decision/models/d3-mini2026-10-14 https://ultrabench.ai/decision/models/d3-nano2026-10-14 https://ultrabench.ai/decision/models/decider-12b-v12026-10-14 https://ultrabench.ai/decision/models/decider-31b2026-10-14 https://ultrabench.ai/decision/models/decider-4b-v22026-10-14 https://ultrabench.ai/decision/models/decider-chat-gemma4-31b2026-10-14 https://ultrabench.ai/decision/models/decider-chat-qwen3-6-27b2026-10-14 https://ultrabench.ai/decision/models/decision-2-0-vega-27b2026-10-14 https://ultrabench.ai/decision/models/fonles-decision-12026-10-14 https://ultrabench.ai/decision/models/gev-26b-decide2026-10-14 https://ultrabench.ai/decision/models/gliner2-5-decide2026-10-14 https://ultrabench.ai/decision/models/gliner2-5-decide-1b2026-10-14 https://ultrabench.ai/decision/models/gliner2-5-multi-decide2026-10-14 https://ultrabench.ai/decision/models/h2o-lightning-4b2026-10-14 https://ultrabench.ai/decision/models/intern-decision-0-8b2026-10-14 https://ultrabench.ai/decision/models/intern-decision-2b2026-10-14 https://ultrabench.ai/decision/models/intern-decision-4b2026-10-14 https://ultrabench.ai/decision/models/jev-1-132026-10-14 https://ultrabench.ai/decision/models/jev-27b2026-10-14 https://ultrabench.ai/decision/models/jev-27b-vl2026-10-14 https://ultrabench.ai/decision/models/jev-35b2026-10-14 https://ultrabench.ai/decision/models/jev-9b2026-10-14 https://ultrabench.ai/decision/models/jev-alpha-26b-a4b2026-10-14 https://ultrabench.ai/decision/models/jev-gemma4-26b-a4b2026-10-14 https://ultrabench.ai/decision/models/jev-style-0-8b-decision-v32026-10-14 https://ultrabench.ai/decision/models/jev-style-2b-v32026-10-14 https://ultrabench.ai/decision/models/jev-typesafe2026-10-14 https://ultrabench.ai/decision/models/jevk52026-10-14 https://ultrabench.ai/decision/models/jevk5-lite2026-10-14 https://ultrabench.ai/decision/models/laya2026-10-14 https://ultrabench.ai/decision/models/laya-multilingual2026-10-14 https://ultrabench.ai/decision/models/laya-typed-decisions2026-10-14 https://ultrabench.ai/decision/models/lev2026-10-14 https://ultrabench.ai/decision/models/mapika-decider-0-8b2026-10-14 https://ultrabench.ai/decision/models/mapika-decider-12b2026-10-14 https://ultrabench.ai/decision/models/mapika-decider-2b2026-10-14 https://ultrabench.ai/decision/models/mapika-decider-35b-a3b2026-10-14 https://ultrabench.ai/decision/models/mapika-decider-4b2026-10-14 https://ultrabench.ai/decision/models/microsoft-decision-12026-10-14 https://ultrabench.ai/decision/models/minicpm5-2b-jev2026-10-14 https://ultrabench.ai/decision/models/nirnaya-0-4b-0-2a-decision2026-10-14 https://ultrabench.ai/decision/models/open-jev-deberta-v3-large2026-10-14 https://ultrabench.ai/decision/models/plumb-4b2026-10-14 https://ultrabench.ai/decision/models/pplx-decider-v1-1-27b2026-10-14 https://ultrabench.ai/decision/models/quyet-1-0-large2026-10-14 https://ultrabench.ai/decision/models/quyet-1-0-medium2026-10-14 https://ultrabench.ai/decision/models/quyet-1-0-small2026-10-14 https://ultrabench.ai/decision/models/quyet-1-0-small-en2026-10-14 https://ultrabench.ai/decision/models/quyet-1-0-tiny2026-10-14 https://ultrabench.ai/decision/models/solar-decide2026-10-14 https://ultrabench.ai/decision/models/span-012026-10-14 https://ultrabench.ai/decision/models/startlux-decision-35b-a3b2026-10-14 https://ultrabench.ai/decision/models/startlux-decision-v1-27b2026-10-14 https://ultrabench.ai/decision/models/startlux-decision-v1-4b2026-10-14 https://ultrabench.ai/decision/models/startlux-decision-v1-9b2026-10-14 https://ultrabench.ai/decision/models/strands-decider-12b-gemma4-v1-26102026-10-14 https://ultrabench.ai/decision/models/strands-decider-26b-a4b-gemma4-v1-26102026-10-14 https://ultrabench.ai/decision/models/strands-decider-2b-hobson-v212026-10-14 https://ultrabench.ai/decision/models/strands-decider-2b-qwen3-5-v1-26102026-10-14 https://ultrabench.ai/decision/models/strands-decider-e2b-gemma4-v1-26102026-10-14 https://ultrabench.ai/decision/models/strands-decider-e4b-gemma4-v1-26102026-10-14 https://ultrabench.ai/decision/models/surogate-rune-26b-a4b2026-10-14 https://ultrabench.ai/decision/models/tev1-0-8b-experimental2026-10-14 https://ultrabench.ai/decision/models/tev1-4b-experimental2026-10-14 https://ultrabench.ai/decision/models/torchcast-decision-12b2026-10-14 https://ultrabench.ai/decision/models/torchcast-decision-27b2026-10-14 https://ultrabench.ai/decision/models/trutina-4b2026-10-14 https://ultrabench.ai/decision/models/winnow-12b2026-10-14 https://ultrabench.ai/decision/models/winnow-e2b2026-10-14 https://ultrabench.ai/decision/models/winnow-e4b2026-10-14 https://ultrabench.ai/decision/models/xor2026-10-14 https://ultrabench.ai/decision/models/xor-26b-a4b-v1-22026-10-21