Leading: LangChain (54.6%)
| Metric | Value |
|---|---|
| GitHub Copilot wins | 269 |
| LangChain wins | 323 |
| Abstains (no tool) | 740 |
| Other tool chosen | 1284 |
| Decisive cases | 592 |
| GitHub Copilot win rate (unweighted) | 45.4% |
| 95% CI | 41.5% - 49.5% |
| GitHub Copilot win rate (weighted) | 45.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | GitHub Copilot | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | Frontier | 93 | 0 | 18 | 29 | 100% |
| Llama 4 Scout | Small | 67 | 9 | 44 | 15 | 88% |
| Gemini 2.5 Flash | Small | 22 | 49 | 59 | 2 | 31% |
| MiMo V2 Pro | Frontier | 14 | 57 | 30 | 31 | 20% |
| DeepSeek R1 0528 | Frontier | 9 | 50 | 52 | 30 | 15% |
| Llama 4 Maverick | Frontier | 10 | 41 | 54 | 36 | 20% |
| Claude Opus 4.6 | Frontier | 0 | 38 | 20 | 74 | 0% |
| Qwen3 Coder Next | Mid | 1 | 34 | 17 | 85 | 3% |
| MiniMax M2.7 | Frontier | 15 | 10 | 25 | 79 | 60% |
| GPT 5.3 Codex | Frontier | 18 | 0 | 25 | 98 | 100% |
| Devstral 2 2512 | Mid | 8 | 10 | 57 | 59 | 44% |
| DeepSeek V3.2 | Mid | 0 | 17 | 52 | 61 | 0% |
| Kimi K2.5 | Frontier | 5 | 0 | 53 | 60 | 100% |
| DeepSeek V4 Flash | Mid | 2 | 2 | 1 | 3 | 50% |
| Mistral Small 4 | Mid | 1 | 3 | 56 | 66 | 25% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 3 | 4 | 100% |
| GPT 5.4 Mini | Mid | 1 | 1 | 7 | 131 | 50% |
| GPT 5.5 | Frontier | 1 | 0 | 1 | 7 | 100% |
| DeepSeek V4 Pro | Frontier | 0 | 1 | 2 | 6 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 1 | 2 | 6 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 68 | 60 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 1 | 8 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 60 | 81 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 8 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 2 | 130 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 9 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 31 | 97 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 9 | n/a |
| Prompt | Tier | GitHub Copilot | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Intermediate | 100 | 39 | 2 | 279 | 72% |
| ai-support-agent-platform | Intermediate | 41 | 82 | 211 | 100 | 33% |
| ai-revenue-ops-copilot | Beginner | 33 | 55 | 231 | 116 | 38% |
| ai-revenue-ops-copilot | Advanced | 21 | 67 | 7 | 313 | 24% |
| ai-support-agent-platform | Advanced | 39 | 40 | 0 | 350 | 49% |
| ai-support-agent-platform | Beginner | 25 | 40 | 289 | 83 | 38% |
| ai-engineering-workflow | Beginner | 4 | 0 | 0 | 15 | 100% |
| ai-engineering-workflow | Advanced | 3 | 0 | 0 | 12 | 100% |
| ai-engineering-workflow | Intermediate | 3 | 0 | 0 | 16 | 100% |
