Asuka-Bench (OpenHands): leaderboard
Asuka-Bench evaluates code agents on 50 web-development tasks given as deliberately underspecified queries, with hidden clarified requirements decomposed into a dependency graph of 784 tasks. This board reports Cumulative weighted task pass rate (%) after three feedback rounds under the OpenHands agent framework, on 50 web-app tasks from underspecified queries verified by a browser UI agent; higher is better.
Metric: Cumulative weighted task pass rate (%) after three feedback rounds under the OpenHands agent framework, on 50 web-app tasks from underspecified queries verified by a browser UI agent; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (Medium) | 90.1 | #123 (GPT-5.4) |
| 2 | Kimi K2.6 | 86.6 | #178 |
| 3 | Gemini 3.1 Pro (Preview) | 80.7 | #94 |
| 4 | GLM-5 | 75.3 | #260 |
| 5 | Qwen 3.5 Plus | 72.9 | #232 |
| 6 | MiniMax-M2.7 | 70.7 | #518 |
| 7 | Seed 2.0 Pro | 53.7 | #211 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=asuka-bench-openhands · How It Works · Data refreshed daily, snapshot 2026-11-13.