Skip to content

Benchmark

RNG-Bench · 3D Maze Explore Rate

Scores are percentages. Higher is better.

Models and systems measured
5
Scores recorded
5
Sources
1
IQ weight
No weight published

Score distribution

25.4%
Mean
21%
Median
7.5%
Std dev
17.9%
10th percentile
36.4%
90th percentile
17.9%
Min
17.9%36.4%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1Gemini 3.1 Pro Previewsingle-player · 13×13 · no minimap · mean optimal path 60 steps· Reported by RNG-Bench / InternLM· via BenchBoard docs36.4%
2GPT 5.4single-player · 13×13 · no minimap · mean optimal path 60 steps· Reported by RNG-Bench / InternLM· via BenchBoard docs32.3%
3Qwen3.5 397B A17Bsingle-player · 13×13 · no minimap · mean optimal path 60 steps· Reported by RNG-Bench / InternLM· via BenchBoard docs21%
4Kimi K2.5single-player · 13×13 · no minimap · mean optimal path 60 steps· Reported by RNG-Bench / InternLM· via BenchBoard docs17.9%

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
Seed-2.0-Litesingle-player · 13×13 · no minimap · mean optimal path 60 steps· Reported by RNG-Bench / InternLM· via BenchBoard docs19.4%

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.