| Metric | Value |
|---|---|
| Cursor wins | 788 |
| LangChain wins | 312 |
| Abstains (no tool) | 715 |
| Other tool chosen | 630 |
| Decisive cases | 1100 |
| Cursor win rate (unweighted) | 71.6% |
| 95% CI | 68.9% - 74.2% |
| Cursor win rate (weighted) | 71.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Cursor | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| GLM 5 Turbo | Frontier | 130 | 0 | 2 | 0 | 100% |
| Claude Opus 4.6 | Frontier | 74 | 38 | 20 | 0 | 66% |
| GPT 5.4 Mini | Mid | 100 | 1 | 7 | 23 | 99% |
| GPT 5.3 Codex | Frontier | 90 | 0 | 25 | 17 | 100% |
| GPT 5.4 | Frontier | 87 | 0 | 31 | 10 | 100% |
| Claude Sonnet 4.6 | Frontier | 74 | 0 | 58 | 0 | 100% |
| DeepSeek V3.2 | Mid | 57 | 17 | 52 | 4 | 77% |
| MiniMax M2.7 | Frontier | 54 | 10 | 25 | 40 | 84% |
| MiMo V2 Pro | Frontier | 4 | 57 | 30 | 41 | 7% |
| Kimi K2.5 | Frontier | 56 | 0 | 53 | 9 | 100% |
| Gemini 2.5 Flash | Small | 2 | 49 | 59 | 22 | 4% |
| DeepSeek R1 0528 | Frontier | 0 | 47 | 51 | 34 | 0% |
| Mistral Small 4 | Mid | 36 | 3 | 54 | 25 | 92% |
| Llama 4 Maverick | Frontier | 0 | 39 | 52 | 41 | 0% |
| Qwen3 Coder Next | Mid | 3 | 33 | 17 | 76 | 8% |
| Devstral 2 2512 | Mid | 6 | 9 | 55 | 55 | 40% |
| Gemini 2.5 Pro | Frontier | 12 | 0 | 18 | 102 | 100% |
| Llama 4 Scout | Small | 0 | 9 | 41 | 79 | 0% |
| Claude Haiku 4.5 | Small | 3 | 0 | 65 | 52 | 100% |
| Prompt | Tier | Cursor | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 185 | 65 | 7 | 132 | 74% |
| ai-revenue-ops-copilot | Intermediate | 200 | 38 | 2 | 160 | 84% |
| ai-support-agent-platform | Advanced | 198 | 40 | 0 | 172 | 83% |
| ai-support-agent-platform | Intermediate | 62 | 78 | 205 | 69 | 44% |
| ai-revenue-ops-copilot | Beginner | 81 | 53 | 222 | 59 | 60% |
| ai-support-agent-platform | Beginner | 62 | 38 | 279 | 38 | 62% |
