Leading: LangGraph (64.9%)
| Metric | Value |
|---|---|
| Intercom wins | 40 |
| LangGraph wins | 74 |
| Abstains (no tool) | 4 |
| Other tool chosen | 879 |
| Decisive cases | 114 |
| Intercom win rate (unweighted) | 35.1% |
| 95% CI | 26.9% - 44.2% |
| Intercom win rate (weighted) | 35.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Intercom | LangGraph | None | Other | A rate |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Frontier | 0 | 24 | 1 | 22 | 0% |
| GLM 5 Turbo | Frontier | 0 | 22 | 2 | 30 | 0% |
| Mistral Small 4 | Mid | 6 | 12 | 0 | 24 | 33% |
| Claude Sonnet 4.6 | Frontier | 4 | 13 | 0 | 37 | 24% |
| Llama 4 Scout | Small | 8 | 0 | 0 | 45 | 100% |
| DeepSeek V3.2 | Mid | 5 | 0 | 0 | 48 | 100% |
| GPT 5.4 | Frontier | 5 | 0 | 0 | 49 | 100% |
| MiniMax M2.7 | Frontier | 4 | 1 | 0 | 47 | 80% |
| Claude Haiku 4.5 | Small | 3 | 0 | 0 | 51 | 100% |
| GPT 5.4 Mini | Mid | 2 | 0 | 0 | 51 | 100% |
| Llama 4 Maverick | Frontier | 2 | 0 | 0 | 51 | 100% |
| Qwen3 Coder Next | Mid | 0 | 2 | 0 | 52 | 0% |
| DeepSeek R1 0528 | Frontier | 1 | 0 | 0 | 52 | 100% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 54 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 52 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 54 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 1 | 53 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 54 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 0 | 53 | n/a |
| Prompt | Tier | Intercom | LangGraph | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Beginner | 40 | 1 | 1 | 123 | 98% |
| ai-revenue-ops-copilot | Intermediate | 0 | 30 | 0 | 137 | 0% |
| ai-support-agent-platform | Advanced | 0 | 15 | 1 | 154 | 0% |
| ai-support-agent-platform | Intermediate | 0 | 14 | 0 | 157 | 0% |
| ai-revenue-ops-copilot | Advanced | 0 | 13 | 2 | 149 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 1 | 0 | 159 | 0% |