| Metric | Value |
|---|---|
| Socket.io wins | 378 |
| Pusher wins | 742 |
| Abstains (no tool) | 47 |
| Other tool chosen | 3600 |
| Decisive cases | 1120 |
| Socket.io win rate (unweighted) | 33.8% |
| 95% CI | 31.0% - 36.6% |
| Socket.io win rate (weighted) | 33.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Socket.io | Pusher | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 97 | 27 | 0 | 127 | 78% |
| Gemini 2.5 Pro | Frontier | 4 | 112 | 0 | 136 | 3% |
| MiMo V2 Pro | Frontier | 9 | 105 | 0 | 128 | 8% |
| GLM 5 Turbo | Frontier | 0 | 110 | 3 | 130 | 0% |
| Claude Haiku 4.5 | Small | 102 | 1 | 0 | 143 | 99% |
| Qwen3 Coder Next | Mid | 0 | 98 | 0 | 153 | 0% |
| Llama 4 Scout | Small | 53 | 41 | 1 | 152 | 56% |
| Claude Opus 4.6 | Frontier | 37 | 36 | 0 | 169 | 51% |
| DeepSeek R1 0528 | Frontier | 5 | 48 | 34 | 163 | 9% |
| Mistral Small 4 | Mid | 0 | 39 | 0 | 211 | 0% |
| MiniMax M2.7 | Frontier | 24 | 14 | 0 | 203 | 63% |
| DeepSeek V3.2 | Mid | 21 | 14 | 1 | 207 | 60% |
| GPT 5.4 | Frontier | 5 | 20 | 0 | 215 | 20% |
| Gemini 2.5 Flash | Small | 4 | 18 | 1 | 220 | 18% |
| Kimi K2.5 | Frontier | 8 | 8 | 5 | 220 | 50% |
| Devstral 2 2512 | Mid | 6 | 8 | 0 | 238 | 43% |
| GPT 5.4 Mini | Mid | 2 | 11 | 2 | 233 | 15% |
| Claude Sonnet 4.6 | Frontier | 0 | 12 | 0 | 240 | 0% |
| GPT 5.3 Codex | Frontier | 1 | 6 | 0 | 245 | 14% |
| Gemini 3.5 Flash | Small | 0 | 4 | 0 | 5 | 0% |
| MiniMax M3 | Frontier | 0 | 4 | 0 | 5 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 2 | 0 | 7 | 0% |
| GLM 5.2 | Frontier | 0 | 2 | 0 | 7 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 1 | 0 | 8 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 1 | 0 | 8 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 0 | 9 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 9 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 0 | 9 | n/a |
| Prompt | Tier | Socket.io | Pusher | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Intermediate | 18 | 133 | 4 | 279 | 12% |
| project-management-tool | Beginner | 65 | 64 | 5 | 303 | 50% |
| social-media-platform | Beginner | 26 | 101 | 17 | 285 | 20% |
| social-media-platform | Advanced | 4 | 112 | 3 | 318 | 3% |
| project-management-tool | Intermediate | 24 | 54 | 3 | 354 | 31% |
| chat-application | Advanced | 25 | 45 | 1 | 363 | 36% |
| social-media-platform | Beginner | 17 | 33 | 3 | 42 | 34% |
| project-management-tool | Beginner | 25 | 24 | 2 | 44 | 51% |
| project-management-tool | Advanced | 17 | 32 | 0 | 388 | 35% |
| social-media-platform | Intermediate | 20 | 28 | 0 | 47 | 42% |
| project-management-tool | Intermediate | 29 | 16 | 0 | 50 | 64% |
| chat-application | Advanced | 27 | 13 | 0 | 55 | 68% |
| chat-application | Intermediate | 30 | 9 | 0 | 56 | 77% |
| social-media-platform | Advanced | 7 | 28 | 0 | 59 | 20% |
| chat-application | Beginner | 18 | 10 | 0 | 67 | 64% |
| chat-application | Intermediate | 11 | 17 | 6 | 402 | 39% |
| project-management-tool | Advanced | 14 | 7 | 0 | 73 | 67% |
| chat-application | Beginner | 1 | 16 | 3 | 415 | 6% |