Benchmark
RNG-Bench · Duel Score
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 22%
- Mean
- 18%
- Median
- 8.3%
- Std dev
- 12.3%
- 10th percentile
- 36.5%
- 90th percentile
- 12.3%
- Min
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro PreviewMatching Pairs · image · poker theme · 16 games per model· Reported by RNG-Bench / InternLM· via BenchBoard docs | 36.5% |
| 2 | GPT 5.4Matching Pairs · image · poker theme · 16 games per model· Reported by RNG-Bench / InternLM· via BenchBoard docs | 25.3% |
| 3 | Kimi K2.5Matching Pairs · image · poker theme · 16 games per model· Reported by RNG-Bench / InternLM· via BenchBoard docs | 18% |
| 4 | Qwen3.5 397B A17BMatching Pairs · image · poker theme · 16 games per model· Reported by RNG-Bench / InternLM· via BenchBoard docs | 18% |
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 |
|---|---|
| Seed-2.0-LiteMatching Pairs · image · poker theme · 16 games per model· Reported by RNG-Bench / InternLM· via BenchBoard docs | 12.3% |