| Metric | Value |
|---|---|
| Apollo GraphQL wins | 144 |
| AWS wins | 148 |
| Abstains (no tool) | 569 |
| Other tool chosen | 3755 |
| Decisive cases | 292 |
| Apollo GraphQL win rate (unweighted) | 49.3% |
| 95% CI | 43.6% - 55.0% |
| Apollo GraphQL win rate (weighted) | 49.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Apollo GraphQL | AWS | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 47 | 2 | 4 | 198 | 96% |
| Gemini 2.5 Pro | Frontier | 23 | 17 | 16 | 194 | 57% |
| MiMo V2 Pro | Frontier | 16 | 20 | 26 | 189 | 44% |
| DeepSeek R1 0528 | Frontier | 1 | 35 | 54 | 161 | 3% |
| Llama 4 Scout | Small | 0 | 23 | 11 | 193 | 0% |
| Claude Haiku 4.5 | Small | 20 | 0 | 15 | 201 | 100% |
| Gemini 2.5 Flash | Small | 5 | 13 | 35 | 194 | 28% |
| GPT 5.3 Codex | Frontier | 0 | 16 | 9 | 225 | 0% |
| GPT 5.4 | Frontier | 9 | 4 | 21 | 213 | 69% |
| DeepSeek V3.2 | Mid | 9 | 3 | 27 | 206 | 75% |
| Qwen3 Coder Next | Mid | 1 | 11 | 79 | 151 | 8% |
| GPT 5.4 Mini | Mid | 5 | 2 | 12 | 204 | 71% |
| MiniMax M2.7 | Frontier | 5 | 1 | 27 | 201 | 83% |
| Kimi K2.5 | Frontier | 3 | 0 | 33 | 200 | 100% |
| GLM 5 Turbo | Frontier | 0 | 1 | 141 | 109 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 11 | 241 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 5 | 246 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 37 | 206 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 6 | 223 | n/a |
| Prompt | Tier | Apollo GraphQL | AWS | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 6 | 68 | 30 | 290 | 8% |
| url-shortener | Advanced | 4 | 68 | 36 | 283 | 6% |
| multi-tenant-crm | Beginner | 61 | 0 | 107 | 219 | 100% |
| multi-tenant-crm | Intermediate | 52 | 6 | 74 | 249 | 90% |
| url-shortener | Beginner | 8 | 2 | 88 | 292 | 80% |
| weather-dashboard | Advanced | 8 | 0 | 4 | 372 | 100% |
| ai-revenue-ops-copilot | Advanced | 2 | 2 | 68 | 302 | 50% |
| url-shortener | Intermediate | 1 | 2 | 65 | 318 | 33% |
| ai-revenue-ops-copilot | Intermediate | 1 | 0 | 72 | 299 | 100% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 24 | 336 | 100% |
| weather-dashboard | Beginner | 0 | 0 | 0 | 399 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 1 | 396 | n/a |