HM-Bench (PCA): leaderboard
Metric: Average accuracy (%) over all tasks of HM-Bench's 19,337 hyperspectral multiple-choice questions (2,178 samples, 13 task categories) with PCA-only input: a false-colour image of the cube's leading principal components; zero-shot, one option letter as output, temperature 0, at most 64 new tokens; higher is better. Source: arxiv.org. Saturation forecast: Around 2034. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 Mini | 42.35 |
| 2 | Claude Sonnet 4.6 | 39.48 |
| 3 | InternVL2-8B | 38.09 |
| 4 | InternVL3-14B | 38.09 |
| 5 | Grok 4 | 32.78 |
| 6 | Qwen 2.5 VL 7B Instruct | 29.36 |
Interactive version: theaggregate.ai/benchmark?slug=hm-bench-pca · How It Works · Data refreshed daily, snapshot 2026-10-07.