Leading: Continue (59.5%)
| Metric | Value |
|---|---|
| GitHub Copilot Workspace wins | 30 |
| Continue wins | 44 |
| Abstains (no tool) | 875 |
| Other tool chosen | 2571 |
| Decisive cases | 74 |
| GitHub Copilot Workspace win rate (unweighted) | 40.5% |
| 95% CI | 30.1% - 51.9% |
| GitHub Copilot Workspace win rate (weighted) | 40.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | GitHub Copilot Workspace | Continue | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 0 | 42 | 63 | 59 | 0% |
| Mistral Small 4 | Mid | 14 | 0 | 69 | 79 | 100% |
| GPT 5.4 Mini | Mid | 7 | 0 | 7 | 173 | 100% |
| Gemini 2.5 Pro | Frontier | 5 | 1 | 21 | 157 | 83% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 6 | 54 | 100% |
| MiniMax M2.7 | Frontier | 1 | 1 | 23 | 98 | 50% |
| Gemini 3.5 Flash | Small | 1 | 0 | 10 | 45 | 100% |
| Claude Haiku 4.5 | Small | 0 | 0 | 82 | 93 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 19 | 107 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 9 | 54 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 74 | 115 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 66 | 119 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 50 | 74 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 14 | 46 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 11 | 52 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 56 | 70 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 2 | 124 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 63 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 26 | 159 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 30 | 92 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 3 | 60 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 50 | 63 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 66 | 121 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 51 | 123 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 29 | 97 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 13 | 50 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 4 | 59 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 21 | 165 | n/a |
| Prompt | Tier | GitHub Copilot Workspace | Continue | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 7 | 23 | 1 | 490 | 23% |
| ai-revenue-ops-copilot | Advanced | 10 | 11 | 7 | 476 | 48% |
| ai-revenue-ops-copilot | Intermediate | 3 | 10 | 2 | 503 | 23% |
| ai-engineering-workflow | Intermediate | 4 | 0 | 0 | 128 | 100% |
| ai-engineering-workflow | Advanced | 3 | 0 | 0 | 107 | 100% |
| ai-support-agent-platform | Intermediate | 2 | 0 | 249 | 282 | 100% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 280 | 252 | 100% |
| ai-engineering-workflow | Beginner | 0 | 0 | 0 | 133 | n/a |
| ai-support-agent-platform | Beginner | 0 | 0 | 336 | 200 | n/a |
