| Metric | Value |
|---|---|
| Twilio wins | 1440 |
| OneSignal wins | 1404 |
| Abstains (no tool) | 101 |
| Other tool chosen | 3445 |
| Decisive cases | 2844 |
| Twilio win rate (unweighted) | 50.6% |
| 95% CI | 48.8% - 52.5% |
| Twilio win rate (weighted) | 50.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Twilio | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 77 | 245 | 1 | 12 | 24% |
| GPT 5.3 Codex | Frontier | 84 | 131 | 0 | 121 | 39% |
| GPT 5.4 | Frontier | 73 | 98 | 0 | 93 | 43% |
| Llama 4 Scout | Small | 86 | 74 | 3 | 168 | 54% |
| Qwen3 Coder Next | Mid | 81 | 79 | 0 | 175 | 51% |
| GPT 5.4 Mini | Mid | 95 | 60 | 8 | 171 | 61% |
| Gemini 2.5 Pro | Frontier | 67 | 75 | 2 | 188 | 47% |
| MiMo V2 Pro | Frontier | 68 | 61 | 4 | 131 | 53% |
| Claude Sonnet 4.6 | Frontier | 61 | 66 | 0 | 209 | 48% |
| DeepSeek V3.2 | Mid | 42 | 84 | 12 | 124 | 33% |
| Claude Opus 4.6 | Frontier | 66 | 59 | 0 | 139 | 53% |
| DeepSeek R1 0528 | Frontier | 62 | 61 | 24 | 187 | 50% |
| Kimi K2.5 | Frontier | 56 | 47 | 7 | 152 | 54% |
| Gemini 2.5 Flash | Small | 65 | 36 | 8 | 154 | 64% |
| GLM 5 Turbo | Frontier | 66 | 33 | 15 | 150 | 67% |
| Claude Haiku 4.5 | Small | 81 | 0 | 0 | 242 | 100% |
| Devstral 2 2512 | Mid | 62 | 10 | 0 | 249 | 86% |
| MiniMax M2.7 | Frontier | 57 | 8 | 14 | 179 | 88% |
| Mistral Small 4 | Mid | 47 | 10 | 1 | 270 | 82% |
| GLM 5.2 | Frontier | 18 | 29 | 0 | 25 | 38% |
| DeepSeek V4 Flash | Mid | 16 | 28 | 0 | 26 | 36% |
| Kimi K2.7 Code | Frontier | 15 | 20 | 0 | 37 | 43% |
| MiniMax M3 | Frontier | 15 | 20 | 0 | 37 | 43% |
| GPT 5.5 | Frontier | 18 | 15 | 0 | 39 | 55% |
| Gemini 3.5 Flash | Small | 17 | 14 | 0 | 41 | 55% |
| MiMo V2.5 Pro | Frontier | 14 | 17 | 2 | 38 | 45% |
| Claude Opus 4.8 | Frontier | 18 | 10 | 0 | 43 | 64% |
| DeepSeek V4 Pro | Frontier | 13 | 14 | 0 | 45 | 48% |
| Prompt | Tier | Twilio | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 513 | 2 | 4 | 16 | 100% |
| restaurant-reservation-system | Intermediate | 493 | 2 | 3 | 39 | 100% |
| restaurant-reservation-system | Advanced | 404 | 7 | 20 | 102 | 98% |
| social-media-platform | Beginner | 1 | 270 | 6 | 260 | 0% |
| social-media-platform | Intermediate | 6 | 252 | 1 | 275 | 2% |
| chat-application | Beginner | 2 | 237 | 14 | 279 | 1% |
| chat-application | Advanced | 10 | 184 | 6 | 334 | 5% |
| chat-application | Intermediate | 0 | 177 | 3 | 355 | 0% |
| social-media-platform | Advanced | 7 | 126 | 5 | 396 | 5% |
| project-management-tool | Beginner | 2 | 56 | 22 | 454 | 3% |
| project-management-tool | Intermediate | 1 | 50 | 13 | 460 | 2% |
| project-management-tool | Advanced | 1 | 41 | 4 | 475 | 2% |