Leading: LangChain (56.1%)
| Metric | Value |
|---|---|
| GitHub Copilot wins | 122 |
| LangChain wins | 156 |
| Abstains (no tool) | 348 |
| Other tool chosen | 598 |
| Decisive cases | 278 |
| GitHub Copilot win rate (unweighted) | 43.9% |
| 95% CI | 38.2% - 49.8% |
| GitHub Copilot win rate (weighted) | 43.9% |
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 | 44 | 0 | 9 | 13 | 100% |
| Llama 4 Scout | Small | 29 | 6 | 21 | 9 | 83% |
| Gemini 2.5 Flash | Small | 11 | 23 | 31 | 1 | 32% |
| MiMo V2 Pro | Frontier | 6 | 26 | 15 | 19 | 19% |
| DeepSeek R1 0528 | Frontier | 3 | 22 | 26 | 15 | 12% |
| Llama 4 Maverick | Frontier | 6 | 18 | 27 | 15 | 25% |
| Claude Opus 4.6 | Frontier | 0 | 21 | 8 | 37 | 0% |
| Qwen3 Coder Next | Mid | 0 | 19 | 8 | 38 | 0% |
| MiniMax M2.7 | Frontier | 8 | 6 | 11 | 39 | 57% |
| GPT 5.3 Codex | Frontier | 11 | 0 | 13 | 42 | 100% |
| DeepSeek V3.2 | Mid | 0 | 8 | 25 | 33 | 0% |
| Devstral 2 2512 | Mid | 1 | 6 | 25 | 31 | 14% |
| Kimi K2.5 | Frontier | 2 | 0 | 24 | 33 | 100% |
| Mistral Small 4 | Mid | 1 | 0 | 28 | 28 | 100% |
| GPT 5.4 Mini | Mid | 0 | 1 | 4 | 61 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 32 | 30 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 28 | 38 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 0 | 66 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 13 | 50 | n/a |
| Prompt | Tier | GitHub Copilot | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Intermediate | 46 | 19 | 1 | 135 | 71% |
| ai-support-agent-platform | Intermediate | 21 | 40 | 97 | 50 | 34% |
| ai-revenue-ops-copilot | Beginner | 16 | 25 | 112 | 54 | 39% |
| ai-revenue-ops-copilot | Advanced | 10 | 31 | 2 | 151 | 24% |
| ai-support-agent-platform | Advanced | 17 | 19 | 0 | 170 | 47% |
| ai-support-agent-platform | Beginner | 12 | 22 | 136 | 38 | 35% |