Benchmark
RecreationBench paper · Overall · Programmatic + visual mean
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 10
- Scores recorded
- 10
- Sources
- 1
- IQ weight
- 1.12
Score distribution
- 33.3%
- Mean
- 34.8%
- Median
- 12.8%
- Std dev
- 21.1%
- 10th percentile
- 44.2%
- 90th percentile
- 9.2%
- Min
This benchmark has a weight of 1.12 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | GPT-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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 58.1% |
| 2 | Claude 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 44.2% |
| 3 | GPT-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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 42.1% |
| 4 | Kimi 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 31.4% |
| 5 | Claude 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 31.1% |
| 6 | GLM 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 24.4% |
| 7 | Gemini 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 21.1% |
| 8 | Qwen3.7 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 9.2% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs | 36.7% |
| 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 · Overall · 250 held-out tasks · equal-weight platform macro average· Reported by QwenLM / RecreationWorld authors· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34.8% |