Benchmark
Causal reflection — TB 2.1 (30 tasks)
Scores are percentages.
Scores from Harbor Hub Leaderboards.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 74.7%
- Mean
- 79.3%
- Median
- 14.4%
- Std dev
- 55.2%
- 10th percentile
- 89.7%
- 90th percentile
- 55.2%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4.1 Flashcampaign· Harbor Hub Leaderboards | 89.7% |
| 2 | GLM 5.3 Flashcampaign· Harbor Hub Leaderboards | 79.3% |
| 3 | Nemotron 3 Ultracampaign· Harbor Hub Leaderboards | 55.2% |