| Metric | Value |
|---|---|
| OpenHands wins | 2 |
| AI SDK wins | 2 |
| Abstains (no tool) | 715 |
| Other tool chosen | 1726 |
| Decisive cases | 4 |
| OpenHands win rate (unweighted) | 50.0% |
| 95% CI | 15.0% - 85.0% |
| OpenHands win rate (weighted) | 50.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | OpenHands | AI SDK | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 | Frontier | 1 | 0 | 31 | 96 | 100% |
| GPT 5.4 Mini | Mid | 1 | 0 | 7 | 123 | 100% |
| DeepSeek V3.2 | Mid | 0 | 1 | 52 | 77 | 0% |
| Devstral 2 2512 | Mid | 0 | 1 | 55 | 69 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 65 | 55 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 20 | 112 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 58 | 74 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 51 | 81 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 59 | 73 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 18 | 114 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 2 | 130 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 25 | 107 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 53 | 65 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 52 | 80 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 41 | 88 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 30 | 102 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 25 | 104 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 54 | 64 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 17 | 112 | n/a |
| Prompt | Tier | OpenHands | AI SDK | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 2 | 0 | 0 | 408 | 100% |
| ai-revenue-ops-copilot | Advanced | 0 | 1 | 7 | 381 | 0% |
| ai-support-agent-platform | Intermediate | 0 | 1 | 205 | 208 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 2 | 398 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 222 | 193 | n/a |
| ai-support-agent-platform | Beginner | 0 | 0 | 279 | 138 | n/a |