| Metric | Value |
|---|---|
| Hex wins | 23 |
| Apache Kafka wins | 32 |
| Abstains (no tool) | 151 |
| Other tool chosen | 2326 |
| Decisive cases | 55 |
| Hex win rate (unweighted) | 41.8% |
| 95% CI | 29.7% - 55.0% |
| Hex win rate (weighted) | 41.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Hex | Apache Kafka | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Opus 4.6 | Frontier | 1 | 18 | 0 | 116 | 5% |
| Mistral Small 4 | Mid | 12 | 0 | 1 | 118 | 100% |
| MiniMax M2.7 | Frontier | 3 | 3 | 14 | 114 | 50% |
| Kimi K2.5 | Frontier | 3 | 1 | 12 | 107 | 75% |
| Llama 4 Maverick | Frontier | 1 | 2 | 0 | 132 | 33% |
| Claude Sonnet 4.6 | Frontier | 0 | 3 | 0 | 132 | 0% |
| Gemini 2.5 Flash | Small | 0 | 3 | 9 | 121 | 0% |
| Devstral 2 2512 | Mid | 2 | 0 | 0 | 132 | 100% |
| GPT 5.4 | Frontier | 1 | 0 | 0 | 133 | 100% |
| Gemini 2.5 Pro | Frontier | 0 | 1 | 9 | 123 | 0% |
| MiMo V2 Pro | Frontier | 0 | 1 | 10 | 124 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 1 | 129 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 49 | 85 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 8 | 126 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 24 | 111 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 134 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 2 | 133 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 10 | 124 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 2 | 132 | n/a |
| Prompt | Tier | Hex | Apache Kafka | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Advanced | 0 | 15 | 2 | 150 | 0% |
| ai-revenue-ops-copilot | Advanced | 13 | 0 | 4 | 142 | 100% |
| fitness-tracking-app | Advanced | 0 | 13 | 2 | 152 | 0% |
| ai-revenue-ops-copilot | Beginner | 8 | 0 | 3 | 156 | 100% |
| multi-tenant-crm | Advanced | 0 | 4 | 15 | 152 | 0% |
| ai-revenue-ops-copilot | Intermediate | 2 | 0 | 1 | 166 | 100% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 169 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 4 | 167 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 11 | 155 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 13 | 158 | n/a |
| saas-application | Intermediate | 0 | 0 | 20 | 151 | n/a |
| saas-application | Beginner | 0 | 0 | 5 | 166 | n/a |
| saas-application | Advanced | 0 | 0 | 9 | 162 | n/a |
| url-shortener | Intermediate | 0 | 0 | 26 | 144 | n/a |
| url-shortener | Beginner | 0 | 0 | 35 | 136 | n/a |
