Leading: Weights & Biases (56.1%)
| Metric | Value |
|---|---|
| Promptfoo wins | 90 |
| Weights & Biases wins | 115 |
| Abstains (no tool) | 183 |
| Other tool chosen | 3434 |
| Decisive cases | 205 |
| Promptfoo win rate (unweighted) | 43.9% |
| 95% CI | 37.3% - 50.7% |
| Promptfoo win rate (weighted) | 43.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Promptfoo | Weights & Biases | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | Small | 0 | 41 | 1 | 85 | 0% |
| Devstral 2 2512 | Mid | 0 | 34 | 14 | 129 | 0% |
| Llama 4 Scout | Small | 0 | 18 | 20 | 147 | 0% |
| MiMo V2 Pro | Frontier | 6 | 10 | 8 | 108 | 38% |
| GLM 5.2 | Frontier | 14 | 0 | 0 | 58 | 100% |
| Gemini 3.5 Flash | Small | 11 | 0 | 7 | 54 | 100% |
| Kimi K2.7 Code | Frontier | 11 | 0 | 1 | 59 | 100% |
| Mistral Small 4 | Mid | 10 | 0 | 3 | 176 | 100% |
| GPT 5.4 Mini | Mid | 9 | 1 | 8 | 183 | 90% |
| DeepSeek R1 0528 | Frontier | 0 | 10 | 9 | 185 | 0% |
| MiMo V2.5 Pro | Frontier | 8 | 0 | 8 | 55 | 100% |
| GLM 5 Turbo | Frontier | 5 | 0 | 19 | 108 | 100% |
| DeepSeek V4 Flash | Mid | 4 | 0 | 4 | 63 | 100% |
| DeepSeek V4 Pro | Frontier | 4 | 0 | 2 | 66 | 100% |
| MiniMax M3 | Frontier | 3 | 0 | 5 | 64 | 100% |
| Kimi K2.5 | Frontier | 2 | 0 | 3 | 114 | 100% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 6 | 64 | 100% |
| GPT 5.3 Codex | Frontier | 1 | 0 | 0 | 203 | 100% |
| GPT 5.5 | Frontier | 1 | 0 | 2 | 69 | 100% |
| Gemini 2.5 Pro | Frontier | 0 | 1 | 11 | 190 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 3 | 191 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 6 | 198 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 22 | 106 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 12 | 177 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 5 | 124 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 4 | 194 | n/a |
| Prompt | Tier | Promptfoo | Weights & Biases | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 7 | 35 | 3 | 469 | 17% |
| ai-revenue-ops-copilot | Intermediate | 11 | 15 | 4 | 492 | 42% |
| ai-support-agent-platform | Advanced | 5 | 19 | 5 | 498 | 21% |
| ai-engineering-workflow | Advanced | 16 | 5 | 1 | 90 | 76% |
| ai-revenue-ops-copilot | Beginner | 5 | 14 | 11 | 496 | 26% |
| ai-engineering-workflow | Beginner | 18 | 0 | 53 | 45 | 100% |
| ai-support-agent-platform | Intermediate | 5 | 13 | 6 | 498 | 28% |
| ai-support-agent-platform | Beginner | 4 | 12 | 73 | 438 | 25% |
| ai-engineering-workflow | Intermediate | 13 | 2 | 1 | 96 | 87% |
| ai-agent-application | Intermediate | 3 | 0 | 1 | 109 | 100% |
| ai-agent-application | Beginner | 2 | 0 | 25 | 92 | 100% |
| ai-agent-application | Advanced | 1 | 0 | 0 | 111 | 100% |
