5-Lens Empirical Quadrants, Pareto Frontier & 17-Facet AI Catalog
Replaces subjective analyst pay-to-play quadrants with reproducible telemetry across LLMs, CPU/Edge SLMs, 3D/Multimodal, Time-Series Foundation Models (Chronos-Bolt, TimesFM 2.0, Moirai-MoE, TimeGPT, PatchTST, Toto), Agent SDKs/Orchestrators, 7-Stage RAG, DSPy, Embeddings, MCP + A2A, Security, Tracing vs Evaluation, Memory Policies vs Vector/SQL Substrates, and Durable Execution.
All 17 Facets (11) agent_development_orchestration ai_security_and_guardrails automation_ipaas_dag_durable embeddings_and_rerankers evaluation_and_regression_testing llm_frontier_cloud llm_open_weights_cloud memory_behavior_policies multimodal_vision_audio_3d observability_tracing_monitoring programmatic_prompt_workflow_optimization protocols_mcp_and_a2a rag_context_pipeline slm_cpu_edge_quantized teleon_team_simulation_provenance timeseries_foundation_models vector_and_transactional_storage
5 Orthogonal Ranking Lenses
- Lens 1 (Empirical 2x2 Quadrant): X = Verified Execution Reliability vs Y = Architectural Composability and Governance Fit.
- Lens 2 (Constraint-Weighted Wave): Custom workload weights plus Tversky hard vetoes (
spdx_license, blast class, CPU-only). - Lens 3 (Exact Pareto Frontier): Non-dominated set across Quality, Latency, Cost, Cliff Retention, and Lock-in Freedom (orange nodes).
- Lens 4 (Jagged-Frontier Cliff Index): Perturbed neighbor retention ratio.
- Lens 5 (Team Marginal Value / WAR): Paired holdout lift net of coordination token tax.
| Component & Publisher | Primary Facet | Quadrant & Frontier | Lens Scores | Cliff & WAR | License |
|---|---|---|---|---|---|
| Sentence Transformers UKPLab / Hugging Face ( embedding_library) |
embeddings_and_rerankers |
EMPIRICAL_LEADER PARETO | Exec: 96, Fit: 94, Wave: 94.48 | Cliff: 93%, WAR: +0.27 | Apache-2.0 |
| BAAI BGE-M3 BAAI ( embedding_model) |
embeddings_and_rerankers |
EMPIRICAL_LEADER PARETO | Exec: 95, Fit: 94, Wave: 94.2 | Cliff: 91%, WAR: +0.29 | MIT |
| Nomic Embed Text v2 MoE Nomic AI ( embedding_model) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 95, Fit: 94, Wave: 93.92 | Cliff: 93%, WAR: +0.26 | Apache-2.0 |
| Snowflake Arctic Embed 2.0 Snowflake ( embedding_model) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 95, Fit: 94, Wave: 93.92 | Cliff: 93%, WAR: +0.26 | Apache-2.0 |
| Jina Reranker v2 Base Multilingual Jina AI ( embedding_model) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 93, Fit: 85, Wave: 90.12 | Cliff: 89%, WAR: +0.24 | CC-BY-NC-4.0 |
| Cohere Rerank 3.5 Cohere ( hosted_embedding_endpoint) |
embeddings_and_rerankers |
EMPIRICAL_LEADER PARETO | Exec: 95, Fit: 94, Wave: 88.88 | Cliff: 91%, WAR: +0.28 | Proprietary |
| Voyage AI voyage-3-large Voyage AI ( hosted_embedding_endpoint) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 94, Fit: 93, Wave: 88.64 | Cliff: 91%, WAR: +0.28 | Proprietary |
| Cohere Embed v4 Cohere ( hosted_embedding_endpoint) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 95, Fit: 94, Wave: 88.56 | Cliff: 91%, WAR: +0.26 | Proprietary |
| OpenAI text-embedding-3-large OpenAI ( hosted_embedding_endpoint) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 95, Fit: 94, Wave: 87.92 | Cliff: 91%, WAR: +0.23 | Proprietary |
| Azure OpenAI Embeddings Microsoft Azure ( hosted_embedding_endpoint) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 95, Fit: 94, Wave: 87.6 | Cliff: 91%, WAR: +0.22 | Proprietary |
| Google Vertex AI Multimodal Embeddings Google Cloud ( hosted_embedding_endpoint) |
embeddings_and_rerankers |
EMPIRICAL_LEADER | Exec: 94, Fit: 93, Wave: 87.36 | Cliff: 91%, WAR: +0.22 | Proprietary |