| Metric | Value |
|---|---|
| Stream wins | 254 |
| Socket.io wins | 378 |
| Abstains (no tool) | 47 |
| Other tool chosen | 4088 |
| Decisive cases | 632 |
| Stream win rate (unweighted) | 40.2% |
| 95% CI | 36.4% - 44.1% |
| Stream win rate (weighted) | 40.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Stream | Socket.io | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 9 | 97 | 0 | 145 | 8% |
| Claude Haiku 4.5 | Small | 0 | 102 | 0 | 144 | 0% |
| Kimi K2.5 | Frontier | 52 | 8 | 5 | 176 | 87% |
| Claude Opus 4.6 | Frontier | 23 | 37 | 0 | 182 | 38% |
| Llama 4 Scout | Small | 0 | 53 | 1 | 193 | 0% |
| Gemini 2.5 Flash | Small | 36 | 4 | 1 | 202 | 90% |
| GPT 5.4 | Frontier | 35 | 5 | 0 | 200 | 88% |
| MiniMax M2.7 | Frontier | 7 | 24 | 0 | 210 | 23% |
| DeepSeek V3.2 | Mid | 6 | 21 | 1 | 215 | 22% |
| GLM 5 Turbo | Frontier | 25 | 0 | 3 | 215 | 100% |
| Claude Sonnet 4.6 | Frontier | 24 | 0 | 0 | 228 | 100% |
| GPT 5.4 Mini | Mid | 16 | 2 | 2 | 228 | 89% |
| MiMo V2 Pro | Frontier | 4 | 9 | 0 | 229 | 31% |
| Gemini 2.5 Pro | Frontier | 6 | 4 | 0 | 242 | 60% |
| DeepSeek R1 0528 | Frontier | 2 | 5 | 34 | 209 | 29% |
| Devstral 2 2512 | Mid | 0 | 6 | 0 | 246 | 0% |
| GPT 5.3 Codex | Frontier | 3 | 1 | 0 | 248 | 75% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 0 | 7 | 100% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 8 | 100% |
| Gemini 3.5 Flash | Small | 1 | 0 | 0 | 8 | 100% |
| GLM 5.2 | Frontier | 1 | 0 | 0 | 8 | 100% |
| GPT 5.5 | Frontier | 1 | 0 | 0 | 8 | 100% |
| DeepSeek V4 Flash | Mid | 0 | 0 | 0 | 9 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 0 | 9 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 0 | 9 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 9 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 0 | 250 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 251 | n/a |
| Prompt | Tier | Stream | Socket.io | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Beginner | 179 | 1 | 3 | 252 | 99% |
| project-management-tool | Beginner | 0 | 65 | 5 | 367 | 0% |
| chat-application | Advanced | 18 | 25 | 1 | 390 | 42% |
| social-media-platform | Beginner | 11 | 26 | 17 | 375 | 30% |
| chat-application | Intermediate | 24 | 11 | 6 | 395 | 69% |
| chat-application | Intermediate | 0 | 30 | 0 | 65 | 0% |
| project-management-tool | Intermediate | 0 | 29 | 0 | 66 | 0% |
| chat-application | Advanced | 0 | 27 | 0 | 68 | 0% |
| chat-application | Beginner | 7 | 18 | 0 | 70 | 28% |
| social-media-platform | Intermediate | 7 | 18 | 4 | 405 | 28% |
| project-management-tool | Beginner | 0 | 25 | 2 | 68 | 0% |
| project-management-tool | Intermediate | 0 | 24 | 3 | 408 | 0% |
| social-media-platform | Intermediate | 0 | 20 | 0 | 75 | 0% |
| project-management-tool | Advanced | 1 | 17 | 0 | 419 | 6% |
| social-media-platform | Beginner | 0 | 17 | 3 | 75 | 0% |
| project-management-tool | Advanced | 0 | 14 | 0 | 80 | 0% |
| social-media-platform | Advanced | 7 | 4 | 3 | 423 | 64% |
| social-media-platform | Advanced | 0 | 7 | 0 | 87 | 0% |