| Metric | Value |
|---|---|
| Arize Phoenix wins | 37 |
| OpenAI wins | 48 |
| Abstains (no tool) | 237 |
| Other tool chosen | 4206 |
| Decisive cases | 85 |
| Arize Phoenix win rate (unweighted) | 43.5% |
| 95% CI | 33.5% - 54.1% |
| Arize Phoenix win rate (weighted) | 43.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Arize Phoenix | OpenAI | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 0 | 2 | 26 | 208 | 0% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 2 | 106 | n/a |
| DeepSeek R1 | Frontier | 0 | 0 | 12 | 228 | n/a |
| Devstral | Mid | 0 | 0 | 19 | 182 | n/a |
| Gemini Flash 2.5–3.8 | Small | 1 | 0 | 12 | 222 | 100% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 0 | 17 | 221 | n/a |
| GLM 5 Turbo–5.3 | Frontier | 0 | 0 | 19 | 221 | n/a |
| GPT 5.4–6 Astra | Frontier | 0 | 11 | 5 | 224 | 0% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 2 | 238 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 6 | 18 | 9 | 204 | 25% |
| Haiku | Small | 0 | 0 | 4 | 227 | n/a |
| Kimi 2.5–3 | Frontier | 0 | 0 | 5 | 221 | n/a |
| Llama Maverick | Frontier | 1 | 2 | 18 | 210 | 33% |
| Llama Scout | Small | 3 | 0 | 29 | 182 | 100% |
| MiMo Pro 2–2.6 | Frontier | 0 | 14 | 17 | 208 | 0% |
| MiniMax M 2.7–3 | Frontier | 5 | 0 | 12 | 219 | 100% |
| Mistral Small | Mid | 5 | 0 | 5 | 216 | 100% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 9 | 230 | n/a |
| Qwen Coder | Mid | 16 | 1 | 4 | 210 | 94% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 11 | 229 | n/a |
| Prompt | Tier | Arize Phoenix | OpenAI | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Beginner | 8 | 17 | 80 | 479 | 32% |
| ai-revenue-ops-copilot | Beginner | 8 | 9 | 13 | 554 | 47% |
| ai-support-agent-platform | Intermediate | 3 | 9 | 6 | 562 | 25% |
| ai-revenue-ops-copilot | Advanced | 6 | 3 | 3 | 562 | 67% |
| ai-revenue-ops-copilot | Intermediate | 5 | 1 | 5 | 569 | 83% |
| ai-engineering-workflow | Advanced | 3 | 3 | 1 | 161 | 50% |
| ai-engineering-workflow | Intermediate | 3 | 0 | 1 | 169 | 100% |
| ai-agent-application | Advanced | 1 | 2 | 0 | 170 | 33% |
| ai-agent-application | Beginner | 0 | 3 | 40 | 135 | 0% |
| ai-support-agent-platform | Advanced | 0 | 1 | 5 | 581 | 0% |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 174 | n/a |
| ai-engineering-workflow | Beginner | 0 | 0 | 82 | 90 | n/a |
