Leading: Arize Phoenix (51.5%)
| Metric | Value |
|---|---|
| Weights & Biases wins | 33 |
| Arize Phoenix wins | 35 |
| Abstains (no tool) | 57 |
| Other tool chosen | 2585 |
| Decisive cases | 68 |
| Weights & Biases win rate (unweighted) | 48.5% |
| 95% CI | 37.1% - 60.2% |
| Weights & Biases win rate (weighted) | 48.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Weights & Biases | Arize Phoenix | None | Other | A rate |
|---|---|---|---|---|---|---|
| MiniMax M2.7 | Frontier | 0 | 15 | 3 | 112 | 0% |
| Qwen3 Coder Next | Mid | 0 | 13 | 1 | 129 | 0% |
| Devstral 2 2512 | Mid | 10 | 1 | 17 | 110 | 91% |
| Llama 4 Scout | Small | 10 | 0 | 14 | 112 | 100% |
| DeepSeek R1 0528 | Frontier | 6 | 0 | 1 | 137 | 100% |
| Gemini 2.5 Flash | Small | 6 | 0 | 1 | 125 | 100% |
| Mistral Small 4 | Mid | 0 | 3 | 1 | 137 | 0% |
| DeepSeek V3.2 | Mid | 0 | 2 | 0 | 130 | 0% |
| MiMo V2.5 Pro | Frontier | 1 | 0 | 0 | 11 | 100% |
| GPT 5.4 Mini | Mid | 0 | 1 | 1 | 142 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 141 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 1 | 11 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 143 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 1 | 10 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 1 | 11 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 6 | 138 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 12 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 0 | 132 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 12 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 144 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 132 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 12 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 4 | 115 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 0 | 12 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 2 | 141 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 2 | 130 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 12 | n/a |
| Prompt | Tier | Weights & Biases | Arize Phoenix | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 10 | 8 | 1 | 416 | 56% |
| ai-revenue-ops-copilot | Advanced | 8 | 6 | 2 | 413 | 57% |
| ai-revenue-ops-copilot | Beginner | 7 | 5 | 29 | 396 | 58% |
| ai-revenue-ops-copilot | Intermediate | 4 | 5 | 1 | 413 | 44% |
| ai-support-agent-platform | Intermediate | 1 | 6 | 1 | 428 | 14% |
| ai-engineering-workflow | Intermediate | 2 | 1 | 0 | 16 | 67% |
| ai-support-agent-platform | Beginner | 0 | 3 | 13 | 417 | 0% |
| ai-engineering-workflow | Advanced | 1 | 1 | 0 | 18 | 50% |
| ai-agent-application | Intermediate | 0 | 0 | 0 | 19 | n/a |
| ai-agent-application | Advanced | 0 | 0 | 0 | 19 | n/a |
| ai-agent-application | Beginner | 0 | 0 | 3 | 17 | n/a |
| ai-engineering-workflow | Beginner | 0 | 0 | 7 | 13 | n/a |