Leading: LangGraph (64.4%)
| Metric | Value |
|---|---|
| Anthropic wins | 145 |
| LangGraph wins | 262 |
| Abstains (no tool) | 93 |
| Other tool chosen | 2961 |
| Decisive cases | 407 |
| Anthropic win rate (unweighted) | 35.6% |
| 95% CI | 31.1% - 40.4% |
| Anthropic win rate (weighted) | 35.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Anthropic | LangGraph | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | Small | 81 | 0 | 0 | 104 | 100% |
| Kimi K2.5 | Frontier | 1 | 60 | 1 | 56 | 2% |
| GLM 5 Turbo | Frontier | 1 | 58 | 2 | 70 | 2% |
| Claude Sonnet 4.6 | Frontier | 0 | 47 | 0 | 139 | 0% |
| Mistral Small 4 | Mid | 11 | 34 | 12 | 92 | 24% |
| Kimi K2.7 Code | Frontier | 9 | 16 | 1 | 26 | 36% |
| Gemini 3.5 Flash | Small | 3 | 22 | 1 | 26 | 12% |
| MiniMax M2.7 | Frontier | 18 | 1 | 0 | 101 | 95% |
| GLM 5.2 | Frontier | 2 | 10 | 1 | 41 | 17% |
| MiniMax M3 | Frontier | 7 | 2 | 0 | 44 | 78% |
| GPT 5.5 | Frontier | 5 | 0 | 0 | 44 | 100% |
| Qwen3 Coder Next | Mid | 2 | 3 | 1 | 177 | 40% |
| Claude Opus 4.6 | Frontier | 0 | 4 | 0 | 128 | 0% |
| GPT 5.3 Codex | Frontier | 3 | 0 | 0 | 182 | 100% |
| MiMo V2.5 Pro | Frontier | 0 | 3 | 4 | 46 | 0% |
| DeepSeek V4 Flash | Mid | 1 | 0 | 7 | 42 | 100% |
| GPT 5.4 Mini | Mid | 1 | 0 | 1 | 182 | 100% |
| Devstral 2 2512 | Mid | 0 | 1 | 12 | 155 | 0% |
| GPT 5.4 | Frontier | 0 | 1 | 0 | 131 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 53 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 15 | 168 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 0 | 131 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 9 | 45 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 132 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 2 | 183 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 18 | 162 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 6 | 171 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 0 | 130 | n/a |
| Prompt | Tier | Anthropic | LangGraph | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Intermediate | 31 | 98 | 1 | 399 | 24% |
| ai-support-agent-platform | Intermediate | 28 | 44 | 0 | 459 | 39% |
| ai-revenue-ops-copilot | Advanced | 5 | 62 | 4 | 443 | 7% |
| ai-support-agent-platform | Advanced | 14 | 43 | 1 | 471 | 25% |
| ai-revenue-ops-copilot | Beginner | 21 | 5 | 0 | 474 | 81% |
| ai-agent-application | Advanced | 15 | 5 | 18 | 78 | 75% |
| ai-support-agent-platform | Beginner | 11 | 5 | 1 | 493 | 69% |
| ai-agent-application | Beginner | 11 | 0 | 35 | 73 | 100% |
| ai-agent-application | Intermediate | 9 | 0 | 33 | 71 | 100% |
