# Arize AI vs BentoML

| Attribute | Arize AI | BentoML |
|---|---|---|
| **Vioscale score** | 70.5 (32% (low)) | 58.1 (43% (low)) |
| activity.commits_last_30d | - | 3 |
| adoption.dependent_repos | - | 499 |
| adoption.github_stars | - | 8,807 |
| deployment.options | `{"cloud":true,"on_prem":true,"self_hosted":true}` | `{"cloud":true,"hybrid":true,"on_prem":true,"self_hosted":true}` |
| description.long | An AI engineering platform that enables teams to observe agent behavior end-to-end, run evaluations at scale, and systematically improve agents through testing and experimentation, available as both a managed cloud service and self-hosted deployment. | An open-source framework for packaging, deploying, and managing AI model inference at scale, supporting any model architecture or framework with options for cloud or on-premises deployment. |
| features.capabilities | `{"role":"platform","evaluation":true,"managed_cloud":true,"self_hostable":true,"multi_provider":true,"vpc_deployment":true,"otel_compatible":true,"llm_observability":true,"prompt_management":true,"framework_agnostic":true,"experiment_tracking":true}` | `{"role":"platform","open_source":true,"managed_cloud":true,"model_serving":true,"self_hostable":true,"multi_provider":true,"vpc_deployment":true,"dynamic_batching":true,"gpu_acceleration":true,"llm_observability":true,"framework_agnostic":true,"multi_model_serving":true,"multi_gpu_multi_node":true,"multi_framework_support":true}` |
| integrations.count | 25 | - |
| integrations.list | `[{"name":"OpenAI"},{"name":"Anthropic"},{"name":"Azure OpenAI"},{"name":"AWS Bedrock"},{"name":"Vertex AI"},{"name":"Google GenAI"},{"name":"NVIDIA NIM"},{"name":"Gemini"},{"name":"OpenRouter"},{"name":"LiteLLM"},{"name":"Claude Code"},{"name":"Cursor"},{"name":"OpenCode"},{"name":"LangGraph"},{"name":"Vercel AI SDK"},{"name":"Mastra"},{"name":"CrewAI"},{"name":"LlamaIndex"},{"name":"DSPy"},{"name":"OpenAI Agents SDK"},{"name":"Claude Agent SDK"},{"name":"BigQuery"},{"name":"Databricks"},{"name":"Snowflake"},{"name":"OpenTelemetry"}]` | - |
| language.primary | - | Python |
| license.spdx | - | Apache-2.0 |
| platform.support | `{"cli":true,"web":true}` | - |
| pricing | - | `{"type":"hybrid","freeTier":true,"sourceUrl":"https://www.bentoml.com","retrievedAt":"2026-08-21T13:19:12.207Z"}` |
| pricing.free_tier | - | yes |
| pricing.model | commercial | commercial |
| pricing.price_level | - | low |
| release.cadence_days | - | 12 |
| release.history | - | `[{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.39","date":"2026-05-07T10:37:29Z","type":"stable","version":"v1.4.39"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.38","date":"2026-04-02T06:12:17Z","type":"stable","version":"v1.4.38"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.37","date":"2026-03-25T01:20:40Z","type":"stable","version":"v1.4.37"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.36","date":"2026-03-06T04:25:28Z","type":"stable","version":"v1.4.36"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.35","date":"2026-02-03T05:06:31Z","type":"stable","version":"v1.4.35"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.34","date":"2026-01-26T03:19:56Z","type":"stable","version":"v1.4.34"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.33","date":"2026-01-12T10:26:47Z","type":"stable","version":"v1.4.33"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.32","date":"2026-01-09T02:22:49Z","type":"stable","version":"v1.4.32"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.31","date":"2025-12-23T06:51:00Z","type":"stable","version":"v1.4.31"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.30","date":"2025-11-27T03:15:11Z","type":"stable","version":"v1.4.30"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.29","date":"2025-11-17T12:02:22Z","type":"stable","version":"v1.4.29"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.28","date":"2025-10-29T06:09:36Z","type":"stable","version":"v1.4.28"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.27","date":"2025-10-20T06:57:33Z","type":"stable","version":"v1.4.27"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.26","date":"2025-10-10T07:28:39Z","type":"stable","version":"v1.4.26"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.25","date":"2025-09-24T08:51:56Z","type":"stable","version":"v1.4.25"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.24","date":"2025-09-17T09:30:34Z","type":"stable","version":"v1.4.24"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.23","date":"2025-09-05T00:51:38Z","type":"stable","version":"v1.4.23"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.22","date":"2025-08-27T01:20:34Z","type":"stable","version":"v1.4.22"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.21","date":"2025-08-14T01:07:36Z","type":"stable","version":"v1.4.21"},{"url":"https://github.com/bentoml/BentoML/releases/tag/v1.4.20","date":"2025-08-13T08:02:48Z","type":"stable","version":"v1.4.20"}]` |
| reliability.status_page | yes | yes |
| security.gdpr | yes | - |
| security.hipaa | yes | - |
| security.iso27001 | yes | - |
| security.pci | yes | - |
| security.scorecard | - | 7 |
| security.soc2 | yes | - |
| security.vulnerabilities | - | `{"count":16,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=bentoml&per_page=100","last_12m":8,"max_severity":"CRITICAL"}` |

## Capabilities (MLOps & LLMOps Tools)

| Capability | Arize AI | BentoML |
|---|:--:|:--:|
| **Core** |  |  |
| Tool role | End-to-end ML platform | End-to-end ML platform |
| **Deployment** |  |  |
| Self-hostable / OSS core | ✓ | ✓ |
| Managed cloud available | ✓ | ✓ |
| On-prem / VPC deployment | ✓ | ✓ |
| **Observability** |  |  |
| LLM tracing / observability | ✓ | ✓ |
| Evaluation (offline / LLM-judge / human) | ✓ | - |
| **Dev** |  |  |
| Prompt management + versioning | ✓ | - |
| **Tracking** |  |  |
| Experiment tracking / model registry | ✓ | - |
| **Serving** |  |  |
| Model serving / inference endpoint | - | ✓ |
| **Interop** |  |  |
| OpenTelemetry / OpenLLMetry compatible | ✓ | - |
| Framework-agnostic | ✓ | ✓ |
| **Gateway** |  |  |
| Multi-provider model support | ✓ | ✓ |
| **Data** |  |  |
| No-train-on-customer-data guarantee | - | - |

*Source: Vioscale. Generated 2026-09-01T16:27:49.737Z. "-" = undocumented, not absent.*