| Metric | Value |
|---|---|
| Arize AI wins | 148 |
| DeepEval wins | 179 |
| Abstains (no tool) | 237 |
| Other tool chosen | 3964 |
| Decisive cases | 327 |
| Arize AI win rate (unweighted) | 45.3% |
| 95% CI | 40.0% - 50.7% |
| Arize AI win rate (weighted) | 45.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Arize AI | DeepEval | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 1 | 29 | 26 | 180 | 3% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 5 | 2 | 101 | 0% |
| DeepSeek R1 | Frontier | 4 | 0 | 12 | 224 | 100% |
| Devstral | Mid | 16 | 5 | 19 | 161 | 76% |
| Gemini Flash 2.5–3.8 | Small | 27 | 0 | 12 | 196 | 100% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 20 | 0 | 17 | 201 | 100% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 0 | 19 | 221 | n/a |
| GPT 5.4–6 Astra | Frontier | 0 | 9 | 5 | 226 | 0% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 2 | 238 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 0 | 9 | 228 | n/a |
| Haiku | Small | 2 | 0 | 4 | 225 | 100% |
| Kimi 2.5–3 | Frontier | 1 | 4 | 5 | 216 | 20% |
| Llama Maverick | Frontier | 15 | 123 | 18 | 75 | 11% |
| Llama Scout | Small | 57 | 0 | 29 | 128 | 100% |
| MiMo Pro 2–2.6 | Frontier | 0 | 4 | 17 | 218 | 0% |
| MiniMax M 2.7–3 | Frontier | 1 | 0 | 12 | 223 | 100% |
| Mistral Small | Mid | 3 | 0 | 5 | 218 | 100% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 9 | 230 | n/a |
| Qwen Coder | Mid | 1 | 0 | 4 | 226 | 100% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 11 | 229 | n/a |
| Prompt | Tier | Arize AI | DeepEval | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 19 | 41 | 5 | 522 | 32% |
| ai-support-agent-platform | Beginner | 23 | 28 | 80 | 453 | 45% |
| ai-support-agent-platform | Intermediate | 21 | 24 | 6 | 529 | 47% |
| ai-revenue-ops-copilot | Advanced | 29 | 13 | 3 | 529 | 69% |
| ai-revenue-ops-copilot | Beginner | 20 | 11 | 13 | 540 | 65% |
| ai-revenue-ops-copilot | Intermediate | 18 | 9 | 5 | 548 | 67% |
| ai-agent-application | Advanced | 8 | 14 | 0 | 151 | 36% |
| ai-engineering-workflow | Advanced | 5 | 15 | 1 | 147 | 25% |
| ai-engineering-workflow | Intermediate | 2 | 11 | 1 | 159 | 15% |
| ai-agent-application | Intermediate | 2 | 7 | 1 | 165 | 22% |
| ai-engineering-workflow | Beginner | 1 | 5 | 82 | 84 | 17% |
| ai-agent-application | Beginner | 0 | 1 | 40 | 137 | 0% |
