Leading: Arize AI (85.6%)
| Metric | Value |
|---|---|
| Weights & Biases wins | 53 |
| Arize AI wins | 315 |
| Abstains (no tool) | 159 |
| Other tool chosen | 4062 |
| Decisive cases | 368 |
| Weights & Biases win rate (unweighted) | 14.4% |
| 95% CI | 11.2% - 18.4% |
| Weights & Biases win rate (weighted) | 14.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Weights & Biases | Arize AI | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 0 | 0 | 4 | 235 | n/a |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 1 | 107 | n/a |
| DeepSeek R1 | Frontier | 8 | 13 | 2 | 217 | 38% |
| Devstral | Mid | 10 | 102 | 29 | 68 | 9% |
| Gemini Flash 2.5–3.8 | Small | 6 | 19 | 4 | 211 | 24% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 1 | 9 | 230 | 0% |
| 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 | 0 | 0 | 6 | 234 | n/a |
| Haiku | Small | 0 | 0 | 3 | 233 | n/a |
| Kimi 2.5–3 | Frontier | 0 | 0 | 4 | 222 | n/a |
| Llama Maverick | Frontier | 0 | 68 | 17 | 153 | 0% |
| Llama Scout | Small | 28 | 69 | 36 | 89 | 29% |
| MiMo Pro 2–2.6 | Frontier | 1 | 4 | 8 | 227 | 20% |
| MiniMax M 2.7–3 | Frontier | 0 | 4 | 5 | 228 | 0% |
| Mistral Small | Mid | 0 | 27 | 4 | 204 | 0% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 9 | 231 | n/a |
| Qwen Coder | Mid | 0 | 8 | 2 | 229 | 0% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 9 | 231 | n/a |
| Prompt | Tier | Weights & Biases | Arize AI | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 10 | 60 | 1 | 521 | 14% |
| ai-support-agent-platform | Intermediate | 2 | 53 | 1 | 538 | 4% |
| ai-revenue-ops-copilot | Intermediate | 4 | 45 | 1 | 528 | 8% |
| ai-revenue-ops-copilot | Beginner | 10 | 34 | 34 | 517 | 23% |
| ai-revenue-ops-copilot | Advanced | 10 | 32 | 3 | 540 | 24% |
| ai-support-agent-platform | Beginner | 1 | 36 | 17 | 535 | 3% |
| ai-engineering-workflow | Advanced | 5 | 20 | 0 | 148 | 20% |
| ai-engineering-workflow | Intermediate | 11 | 10 | 0 | 156 | 52% |
| ai-agent-application | Intermediate | 0 | 14 | 1 | 160 | 0% |
| ai-agent-application | Advanced | 0 | 6 | 0 | 169 | 0% |
| ai-agent-application | Beginner | 0 | 4 | 27 | 147 | 0% |
| ai-engineering-workflow | Beginner | 0 | 1 | 74 | 103 | 0% |
