List your company

Language Model Routing and Orchestration on Blind pool

74.3Average Precision (p@1)Direct Claude Opus
31.129642.337353.54564.7527May 6, 2026

Evaluation results

MethodLinks
Direct Claude OpusFamily=Single model, Role in comparison=frontier direct upper bound2026.0574.35.5831,847.3
AGENTORCHESTRAFamily=Workflow/agentic, Role in comparison=heavy multi-agent orchestration2026.0567.21.22811,650.8
AOrchestraFamily=Workflow/agentic, Role in comparison=agentic workflow orchestration2026.0563.971.00391,530.3
xRouterFamily=Single-turn router, Role in comparison=strong one-shot learned router2026.0554.720.25574.1
SkillOrchestraFamily=Skill-aware, Role in comparison=skill competence-cost orchestration2026.0552.610.1879522.1
MasRouterFamily=MAS routing, Role in comparison=roles/collaboration/model routing2026.0551.710.3128600
GraphRouterFamily=Single-turn router, Role in comparison=graph/representation router2026.0551.610.3045573.5
ICL-RouterFamily=Single-turn router, Role in comparison=training-free in-context router2026.0549.850.2111516.1
PromptLLMFamily=Multi-turn router, Role in comparison=prompted LLM-as-router2026.0549.740.8959732.7
ATLAS (cluster)Family=Single-turn router, Role in comparison=cluster/profile router2026.0549.30.4042650.5
RouterDCFamily=Single-turn router, Role in comparison=contrastive query-to-model router2026.0547.330.2155520
Tool OrchestraFamily=Workflow/agentic, Role in comparison=tool workflow orchestration2026.0545.740.79331,778.2
ColdStartLLMRouterFamily=Single-turn router, Role in comparison=cold-start low-data router2026.0542.410.226530.3
AutoMixFamily=Cascade/mix, Role in comparison=adaptive cascade inference2026.0540.860.29081,228.2
KNNMultiRoundRouterFamily=Multi-turn router, Role in comparison=retrieval-based multi-round router2026.0538.890.2006542.8
ToolLLMFamily=Tool-use model, Role in comparison=tool-specialized model2026.0532.790.1359656.6