multimodal benchmark
RecreationBench Leaderboard
RecreationBench is Qwen's long-horizon application-recreation benchmark for hybrid agents across Ubuntu, macOS, Windows, Android, and the web.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
RecreationBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score49.90% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score49.90% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score47.10% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
RecreationBench Highlights
The leading models and scores on this benchmark.
RecreationBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for RecreationBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is RecreationBench?
What RecreationBench measures and how its scores work.
RecreationBench is a multimodal benchmark for application recreation across Ubuntu, macOS, Windows, Android, and the web.
It measures application-recreation performance using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- RecreationBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about RecreationBench.
Which model scores highest on RecreationBench?
Qwen3.8-Flash-Next is currently ranked first with 49.90%.
What are the top three models on RecreationBench?
The current leaders are Qwen3.8-Flash-Next (49.90%), Qwen3.8 Flash (49.90%), and Qwen3.8-27B (47.10%).
Which RecreationBench model has the lowest official input price?
Qwen3.8 Flash has the lowest matched official input price at $0.15 input / $0.47 output per 1M tokens.
Which models are fastest among RecreationBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.