Skip to content

Benchmark

RNG-Bench · Matching Pairs Score

Scores are percentages. Higher is better.

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

Score distribution

43.8%
Mean
43.2%
Median
12.3%
Std dev
25.3%
10th percentile
62.3%
90th percentile
25.3%
Min
25.3%62.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1GPT 5.4single-player · 10×10 · image · noise theme· Reported by RNG-Bench / InternLM· via BenchBoard docs62.3%
2Gemini 3.1 Pro Previewsingle-player · 10×10 · image · noise theme· Reported by RNG-Bench / InternLM· via BenchBoard docs50%
3Kimi K2.5single-player · 10×10 · image · noise theme· Reported by RNG-Bench / InternLM· via BenchBoard docs38%
4Qwen3.5 397B A17Bsingle-player · 10×10 · image · noise theme· Reported by RNG-Bench / InternLM· via BenchBoard docs25.3%

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 · 10×10 · image · noise theme· Reported by RNG-Bench / InternLM· via BenchBoard docs43.2%

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.