Benchmark
Mercury Single-shot Leaderboard
Scores are percentages.
Scores from Harbor Hub Leaderboards.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.96
Score distribution
- 90.5%
- Mean
- 92.2%
- Median
- 3.9%
- Std dev
- 85.6%
- 10th percentile
- 93.9%
- 90th percentile
- 81.2%
- Min
This benchmark has a weight of 1.96 for chat models, measured over 6 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 | GPT-6 Astramain· Harbor Hub Leaderboards | 94.2% |
| 2 | Claude Opus 5.5main· Harbor Hub Leaderboards | 93.4% |
| 3 | GPT-6 Solmain· Harbor Hub Leaderboards | 92.2% |
| 4 | Claude Sonnet 5.5main· Harbor Hub Leaderboards | 91.5% |
| 5 | GPT-6 Lunamain· Harbor Hub Leaderboards | 85.6% |
| 6 | Claude Haiku 4.5main· Harbor Hub Leaderboards | 81.2% |