| Metric | Value |
|---|---|
| Promptfoo wins | 11 |
| Braintrust wins | 303 |
| Abstains (no tool) | 36 |
| Other tool chosen | 650 |
| Decisive cases | 314 |
| Promptfoo win rate (unweighted) | 3.5% |
| 95% CI | 2.0% - 6.2% |
| Promptfoo win rate (weighted) | 3.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Promptfoo | Braintrust | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 0 | 51 | 0 | 3 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 46 | 0 | 8 | 0% |
| Kimi K2.5 | Frontier | 1 | 44 | 0 | 3 | 2% |
| Claude Haiku 4.5 | Small | 0 | 44 | 1 | 7 | 0% |
| GPT 5.4 | Frontier | 0 | 39 | 0 | 15 | 0% |
| GLM 5 Turbo | Frontier | 4 | 32 | 7 | 11 | 11% |
| Claude Sonnet 4.6 | Frontier | 0 | 28 | 0 | 26 | 0% |
| MiniMax M2.7 | Frontier | 0 | 17 | 1 | 34 | 0% |
| Mistral Small 4 | Mid | 4 | 0 | 0 | 47 | 100% |
| MiMo V2 Pro | Frontier | 2 | 1 | 2 | 49 | 67% |
| GPT 5.4 Mini | Mid | 0 | 1 | 1 | 52 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 2 | 52 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 9 | 43 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 1 | 50 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 52 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 6 | 48 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 53 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 3 | 46 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 3 | 51 | n/a |
| Prompt | Tier | Promptfoo | Braintrust | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 2 | 63 | 4 | 99 | 3% |
| ai-revenue-ops-copilot | Advanced | 2 | 63 | 1 | 98 | 3% |
| ai-revenue-ops-copilot | Intermediate | 4 | 49 | 1 | 110 | 8% |
| ai-support-agent-platform | Advanced | 1 | 52 | 1 | 115 | 2% |
| ai-support-agent-platform | Intermediate | 2 | 37 | 4 | 123 | 5% |
| ai-support-agent-platform | Beginner | 0 | 39 | 25 | 105 | 0% |
