Benchmark
Realtime games
Scores are percentages.
Scores from Harbor Hub Leaderboards.
- Models measured
- 8
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 0.00
Score distribution
- 40%
- Mean
- 50%
- Median
- 10%
- Std dev
- 30%
- 10th percentile
- 50%
- 90th percentile
- 30%
- Min
This benchmark has a weight of 0.00 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 | Score |
|---|---|---|
| 1 | Claude Haiku 5.5main· Harbor Hub Leaderboards | 50% |
| 2 | Claude Sonnet 5.5main· Harbor Hub Leaderboards | 50% |
| 3 | GPT-6.1 Terramain· Harbor Hub Leaderboards | 50% |
| 4 | GPT-6.2 Astramain· Harbor Hub Leaderboards | 50% |
| 5 | Claude Fable 5.2main· Harbor Hub Leaderboards | 30% |
| 6 | Claude Opus 5.5main· Harbor Hub Leaderboards | 30% |
| 7 | GPT-6 Lunamain· Harbor Hub Leaderboards | 30% |
| 8 | GPT-6.2 Solmain· Harbor Hub Leaderboards | 30% |