Skip to content

Benchmark

RecreationBench paper · Web · Applications with Prog =100%

Higher scores are better.

Models and systems measured
10
Scores recorded
10
Sources
1
IQ weight
No weight published

Score distribution

0
Mean
0
Median
0
Std dev
0
10th percentile
0
90th percentile
0
Min

Leaderboard

#Model or systemScore
1Claude Opus 4.8RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
2Claude Opus 5RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
3Gemini 3.7 FlashRecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
4GLM 5.3RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
5GPT-5.6 SolRecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 272k context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
6GPT-6 AstraRecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 272k context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
7Kimi K3RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
8Qwen3.7 PlusRecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · thinking enabled per site data · 256k context · 32k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Grok 4.6RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · xhigh reasoning effort per site data · 500k context · 128k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs0
Qwen3.8 Max 0902RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · xhigh reasoning effort per site data · 256k context · 32k max output tokens · Web · nominal 50-task split · platform-specific score· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.