Benchmark
FrontierBioML
Scores are percentages.
Scores from Harbor Hub Leaderboards.
- Models measured
- 10
- Scores recorded
- 10
- Sources
- 1
- IQ weight
- 1.69
Score distribution
- 28%
- Mean
- 28.8%
- Median
- 7.8%
- Std dev
- 22.4%
- 10th percentile
- 36.8%
- 90th percentile
- 11%
- Min
This benchmark has a weight of 1.69 for chat models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | |
|---|---|---|
| 1 | Gemini 4 Carbonmain· Harbor Hub Leaderboards | 39% |
| 2 | Gemini 4 Argonmain· Harbor Hub Leaderboards | 36.8% |
| 3 | Claude Opus 5.5main· Harbor Hub Leaderboards | 36.5% |
| 4 | GPT-6.1 Solmain· Harbor Hub Leaderboards | 29.1% |
| 5 | GPT-6 Astramain· Harbor Hub Leaderboards | 28.8% |
| 6 | Muse Wondermain· Harbor Hub Leaderboards | 26.9% |
| 7 | Kimi K3.1 Promain· Harbor Hub Leaderboards | 25.8% |
| 8 | Grok 4.7main· Harbor Hub Leaderboards | 24% |
| 9 | DeepSeek V4.1 Flashmain· Harbor Hub Leaderboards | 22.4% |
| 10 | Nemotron 3.5 Super VLmain· Harbor Hub Leaderboards | 11% |
Tokens per task, input and output together, as measured by the source. Comparable within this benchmark only.