| Metric | Value |
|---|---|
| OneSignal wins | 1404 |
| Twilio wins | 1440 |
| Abstains (no tool) | 101 |
| Other tool chosen | 3445 |
| Decisive cases | 2844 |
| OneSignal win rate (unweighted) | 49.4% |
| 95% CI | 47.5% - 51.2% |
| OneSignal win rate (weighted) | 49.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | OneSignal | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 245 | 77 | 1 | 12 | 76% |
| GPT 5.3 Codex | Frontier | 131 | 84 | 0 | 121 | 61% |
| GPT 5.4 | Frontier | 98 | 73 | 0 | 93 | 57% |
| Qwen3 Coder Next | Mid | 79 | 81 | 0 | 175 | 49% |
| Llama 4 Scout | Small | 74 | 86 | 3 | 168 | 46% |
| GPT 5.4 Mini | Mid | 60 | 95 | 8 | 171 | 39% |
| Gemini 2.5 Pro | Frontier | 75 | 67 | 2 | 188 | 53% |
| MiMo V2 Pro | Frontier | 61 | 68 | 4 | 131 | 47% |
| Claude Sonnet 4.6 | Frontier | 66 | 61 | 0 | 209 | 52% |
| DeepSeek V3.2 | Mid | 84 | 42 | 12 | 124 | 67% |
| Claude Opus 4.6 | Frontier | 59 | 66 | 0 | 139 | 47% |
| DeepSeek R1 0528 | Frontier | 61 | 62 | 24 | 187 | 50% |
| Kimi K2.5 | Frontier | 47 | 56 | 7 | 152 | 46% |
| Gemini 2.5 Flash | Small | 36 | 65 | 8 | 154 | 36% |
| GLM 5 Turbo | Frontier | 33 | 66 | 15 | 150 | 33% |
| Claude Haiku 4.5 | Small | 0 | 81 | 0 | 242 | 0% |
| Devstral 2 2512 | Mid | 10 | 62 | 0 | 249 | 14% |
| MiniMax M2.7 | Frontier | 8 | 57 | 14 | 179 | 12% |
| Mistral Small 4 | Mid | 10 | 47 | 1 | 270 | 18% |
| GLM 5.2 | Frontier | 29 | 18 | 0 | 25 | 62% |
| DeepSeek V4 Flash | Mid | 28 | 16 | 0 | 26 | 64% |
| Kimi K2.7 Code | Frontier | 20 | 15 | 0 | 37 | 57% |
| MiniMax M3 | Frontier | 20 | 15 | 0 | 37 | 57% |
| GPT 5.5 | Frontier | 15 | 18 | 0 | 39 | 45% |
| MiMo V2.5 Pro | Frontier | 17 | 14 | 2 | 38 | 55% |
| Gemini 3.5 Flash | Small | 14 | 17 | 0 | 41 | 45% |
| Claude Opus 4.8 | Frontier | 10 | 18 | 0 | 43 | 36% |
| DeepSeek V4 Pro | Frontier | 14 | 13 | 0 | 45 | 52% |
| Prompt | Tier | OneSignal | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 2 | 513 | 4 | 16 | 0% |
| restaurant-reservation-system | Intermediate | 2 | 493 | 3 | 39 | 0% |
| restaurant-reservation-system | Advanced | 7 | 404 | 20 | 102 | 2% |
| social-media-platform | Beginner | 270 | 1 | 6 | 260 | 100% |
| social-media-platform | Intermediate | 252 | 6 | 1 | 275 | 98% |
| chat-application | Beginner | 237 | 2 | 14 | 279 | 99% |
| chat-application | Advanced | 184 | 10 | 6 | 334 | 95% |
| chat-application | Intermediate | 177 | 0 | 3 | 355 | 100% |
| social-media-platform | Advanced | 126 | 7 | 5 | 396 | 95% |
| project-management-tool | Beginner | 56 | 2 | 22 | 454 | 97% |
| project-management-tool | Intermediate | 50 | 1 | 13 | 460 | 98% |
| project-management-tool | Advanced | 41 | 1 | 4 | 475 | 98% |