Leading: LangChain (79.3%)
| Metric | Value |
|---|---|
| LangGraph wins | 185 |
| LangChain wins | 709 |
| Abstains (no tool) | 6 |
| Other tool chosen | 1528 |
| Decisive cases | 894 |
| LangGraph win rate (unweighted) | 20.7% |
| 95% CI | 18.2% - 23.5% |
| LangGraph win rate (weighted) | 20.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | LangGraph | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 0 | 114 | 0 | 13 | 0% |
| GLM 5 Turbo | Frontier | 58 | 34 | 2 | 37 | 63% |
| Kimi K2.5 | Frontier | 60 | 27 | 1 | 30 | 69% |
| Gemini 2.5 Pro | Frontier | 0 | 87 | 2 | 43 | 0% |
| Llama 4 Scout | Small | 0 | 80 | 0 | 47 | 0% |
| Claude Sonnet 4.6 | Frontier | 33 | 43 | 0 | 56 | 43% |
| Claude Opus 4.6 | Frontier | 4 | 65 | 0 | 63 | 6% |
| Mistral Small 4 | Mid | 26 | 36 | 0 | 40 | 42% |
| Qwen3 Coder Next | Mid | 2 | 59 | 0 | 68 | 3% |
| Devstral 2 2512 | Mid | 0 | 54 | 0 | 75 | 0% |
| Gemini 2.5 Flash | Small | 0 | 44 | 0 | 88 | 0% |
| DeepSeek V3.2 | Mid | 0 | 40 | 0 | 91 | 0% |
| MiMo V2 Pro | Frontier | 0 | 13 | 0 | 117 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 8 | 0 | 121 | 0% |
| MiniMax M2.7 | Frontier | 1 | 2 | 0 | 117 | 33% |
| Claude Haiku 4.5 | Small | 0 | 3 | 0 | 128 | 0% |
| GPT 5.4 | Frontier | 1 | 0 | 0 | 131 | 100% |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 132 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 1 | 131 | n/a |
| Prompt | Tier | LangGraph | LangChain | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Intermediate | 70 | 178 | 1 | 163 | 28% |
| ai-revenue-ops-copilot | Advanced | 44 | 169 | 3 | 187 | 21% |
| ai-support-agent-platform | Advanced | 32 | 139 | 1 | 239 | 19% |
| ai-support-agent-platform | Intermediate | 30 | 137 | 0 | 247 | 18% |
| ai-revenue-ops-copilot | Beginner | 4 | 51 | 0 | 333 | 7% |
| ai-support-agent-platform | Beginner | 5 | 35 | 1 | 359 | 13% |
