| Metric | Value |
|---|---|
| Patronus AI wins | 7 |
| Helicone wins | 7 |
| Abstains (no tool) | 194 |
| Other tool chosen | 3729 |
| Decisive cases | 14 |
| Patronus AI win rate (unweighted) | 50.0% |
| 95% CI | 26.8% - 73.2% |
| Patronus AI win rate (weighted) | 50.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Patronus AI | Helicone | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 0 | 5 | 14 | 176 | 0% |
| MiMo V2 Pro | Frontier | 4 | 0 | 8 | 114 | 100% |
| Gemini 2.5 Pro | Frontier | 2 | 0 | 9 | 197 | 100% |
| GPT 5.4 | Frontier | 1 | 0 | 0 | 125 | 100% |
| DeepSeek V3.2 | Mid | 0 | 1 | 22 | 100 | 0% |
| Devstral 2 2512 | Mid | 0 | 1 | 14 | 157 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 4 | 196 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 126 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 7 | 76 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 7 | 203 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 10 | 200 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 4 | 79 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 2 | 82 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 1 | 120 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 8 | 76 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 19 | 107 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 84 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 210 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 8 | 199 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 3 | 81 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 3 | 111 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 1 | 82 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 23 | 166 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 9 | 74 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 5 | 118 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 6 | 78 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 3 | 193 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 4 | 199 | n/a |
| Prompt | Tier | Patronus AI | Helicone | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 4 | 2 | 2 | 508 | 67% |
| ai-revenue-ops-copilot | Intermediate | 0 | 3 | 4 | 516 | 0% |
| ai-support-agent-platform | Advanced | 2 | 0 | 5 | 520 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 2 | 11 | 512 | 0% |
| ai-support-agent-platform | Beginner | 1 | 0 | 75 | 452 | 100% |
| ai-agent-application | Advanced | 0 | 0 | 0 | 131 | n/a |
| ai-agent-application | Beginner | 0 | 0 | 28 | 110 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 131 | n/a |
| ai-engineering-workflow | Advanced | 0 | 0 | 1 | 129 | n/a |
| ai-engineering-workflow | Beginner | 0 | 0 | 61 | 73 | n/a |
| ai-engineering-workflow | Intermediate | 0 | 0 | 1 | 130 | n/a |
| ai-support-agent-platform | Intermediate | 0 | 0 | 5 | 517 | n/a |