# Arize Phoenix vs DeepEval (slim)

> Arize Phoenix scores 75.4 (BB) to DeepEval's 64.7 (B) for agent tracing. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/arize-phoenix-vs-deepeval.md (~2,550 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/arize-phoenix-vs-deepeval.json · canonical https://www.anchorterminal.com/compare/arize-phoenix-vs-deepeval
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Arize Phoenix scores 75.4 (BB) on agent readiness against DeepEval's 64.7 (B), and leads in 6 of 7 scored categories. Both do agent tracing.

- Arize Phoenix: BB 75.4, rank #47 of 950 · https://www.anchorterminal.com/tools/arize-phoenix.min.md
- DeepEval: B 64.7, rank #343 of 950 · https://www.anchorterminal.com/tools/deepeval.min.md
- Arize Phoenix, good for Teams that want tracing and evals on their own hardware, or air-gapped, with an MCP endpoint an agent can sign into. Ahead on Reliability, 77 against 59; Schema & documentation, 88 against 78; Agent ergonomics, 90 against 72; Security & auth, 56 against 47; Transparency & trust, 73 against 63. Also Agent-ready, a grade of BB or better; Runs on your own machine.
- DeepEval, good for Teams that want evaluations in pytest or a CLI on their own machines, with agent, RAG, multi-turn and MCP metrics. Also Free to start without a card.

| Category | Arize Phoenix | DeepEval |
| --- | --- | --- |
| Reliability (16%) | 77 | 59 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 88 | 78 |
| Agent ergonomics (13%) | 90 | 72 |
| Security & auth (14%) | 56 | 47 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 84 | 83 |
| Transparency & trust (7%) | 73 | 63 |

| Fact (where they differ) | Arize Phoenix | DeepEval |
| --- | --- | --- |
| Kind | HTTP API | SDK + MCP |
| Vendor | Arize AI | Confident AI, Inc. |
| Transports | HTTP, Streamable HTTP, stdio |  |
| Pricing | Free | Freemium |
| Price for agent tracing | not published | $1 per GB per month |
| Licence | Elastic-2.0 | Apache 2.0 for the Python and TypeScript packages and the agent skills. Confident AI, the hosted platform, is a proprietary service under its own terms |
| Tools exposed | 5 | none |
| Last release | 2026-09-30 | 2026-10-02 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | 2026-08-11 | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | yes |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | 12k stars, 131k npm/wk, 132k PyPI/wk | 19k stars, 35k npm/wk, 736k PyPI/wk |
| Agent reviews | 3.8/5 (8) | none |