Leading: Weights & Biases (51.1%)
| Metric | Value |
|---|---|
| DeepEval wins | 92 |
| Weights & Biases wins | 96 |
| Abstains (no tool) | 90 |
| Other tool chosen | 2166 |
| Decisive cases | 188 |
| DeepEval win rate (unweighted) | 48.9% |
| 95% CI | 41.9% - 56.0% |
| DeepEval win rate (weighted) | 48.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | DeepEval | Weights & Biases | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 78 | 0 | 0 | 49 | 100% |
| Gemini 2.5 Flash | Small | 0 | 41 | 1 | 85 | 0% |
| Devstral 2 2512 | Mid | 0 | 25 | 4 | 96 | 0% |
| Llama 4 Scout | Small | 0 | 11 | 4 | 106 | 0% |
| MiMo V2 Pro | Frontier | 0 | 10 | 8 | 114 | 0% |
| GPT 5.4 | Frontier | 9 | 0 | 0 | 123 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 7 | 7 | 118 | 0% |
| Kimi K2.5 | Frontier | 4 | 0 | 3 | 112 | 100% |
| DeepSeek V3.2 | Mid | 1 | 0 | 22 | 105 | 100% |
| Gemini 2.5 Pro | Frontier | 0 | 1 | 9 | 122 | 0% |
| GPT 5.4 Mini | Mid | 0 | 1 | 3 | 128 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 1 | 124 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 19 | 113 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 132 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 5 | 124 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 1 | 123 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 3 | 128 | n/a |
| Prompt | Tier | DeepEval | Weights & Biases | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 32 | 19 | 5 | 354 | 63% |
| ai-revenue-ops-copilot | Advanced | 9 | 31 | 2 | 358 | 23% |
| ai-support-agent-platform | Beginner | 21 | 12 | 64 | 314 | 64% |
| ai-support-agent-platform | Intermediate | 20 | 10 | 5 | 374 | 67% |
| ai-revenue-ops-copilot | Beginner | 6 | 14 | 10 | 380 | 30% |
| ai-revenue-ops-copilot | Intermediate | 4 | 10 | 4 | 386 | 29% |
