Leading: Datadog (51.5%)
| Metric | Value |
|---|---|
| Arize Phoenix wins | 50 |
| Datadog wins | 53 |
| Abstains (no tool) | 159 |
| Other tool chosen | 4327 |
| Decisive cases | 103 |
| Arize Phoenix win rate (unweighted) | 48.5% |
| 95% CI | 39.1% - 58.1% |
| Arize Phoenix win rate (weighted) | 48.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Arize Phoenix | Datadog | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 2 | 2 | 4 | 231 | 50% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 1 | 107 | n/a |
| DeepSeek R1 | Frontier | 0 | 0 | 2 | 238 | n/a |
| Devstral | Mid | 3 | 0 | 29 | 177 | 100% |
| Gemini Flash 2.5–3.8 | Small | 1 | 44 | 4 | 191 | 2% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 0 | 9 | 231 | n/a |
| GLM 5 Turbo–5.3 | Frontier | 0 | 0 | 0 | 240 | n/a |
| GPT 5.4–6 Astra | Frontier | 0 | 0 | 5 | 235 | n/a |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 2 | 238 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 1 | 0 | 6 | 233 | 100% |
| Haiku | Small | 0 | 4 | 3 | 229 | 0% |
| Kimi 2.5–3 | Frontier | 0 | 0 | 4 | 222 | n/a |
| Llama Maverick | Frontier | 0 | 0 | 17 | 221 | n/a |
| Llama Scout | Small | 0 | 1 | 36 | 185 | 0% |
| MiMo Pro 2–2.6 | Frontier | 0 | 1 | 8 | 231 | 0% |
| MiniMax M 2.7–3 | Frontier | 15 | 0 | 5 | 217 | 100% |
| Mistral Small | Mid | 8 | 1 | 4 | 222 | 89% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 9 | 231 | n/a |
| Qwen Coder | Mid | 20 | 0 | 2 | 217 | 100% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 9 | 231 | n/a |
| Prompt | Tier | Arize Phoenix | Datadog | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 9 | 18 | 1 | 564 | 33% |
| ai-revenue-ops-copilot | Advanced | 10 | 16 | 3 | 556 | 38% |
| ai-revenue-ops-copilot | Beginner | 5 | 13 | 34 | 543 | 28% |
| ai-support-agent-platform | Intermediate | 8 | 1 | 1 | 584 | 89% |
| ai-engineering-workflow | Advanced | 7 | 1 | 0 | 165 | 88% |
| ai-support-agent-platform | Beginner | 3 | 4 | 17 | 565 | 43% |
| ai-revenue-ops-copilot | Intermediate | 5 | 0 | 1 | 572 | 100% |
| ai-engineering-workflow | Intermediate | 3 | 0 | 0 | 174 | 100% |
| ai-agent-application | Advanced | 0 | 0 | 0 | 175 | n/a |
| ai-agent-application | Beginner | 0 | 0 | 27 | 151 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 174 | n/a |
| ai-engineering-workflow | Beginner | 0 | 0 | 74 | 104 | n/a |