HM-Bench (RGB): leaderboard
Metric: Average accuracy (%) over all tasks of HM-Bench's 19,337 hyperspectral multiple-choice questions (2,178 samples, 13 task categories) with RGB-only input: a pseudo-RGB rendering of the hyperspectral cube; 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 | InternVL3-14B | 42.48 |
| 2 | Claude Sonnet 4.6 | 40.95 |
| 3 | GPT-5.4 Mini | 39.88 |
| 4 | Qwen 2.5 VL 7B Instruct | 38.19 |
| 5 | InternVL2-8B | 36.63 |
| 6 | Grok 4 | 34.67 |
Interactive version: theaggregate.ai/benchmark?slug=hm-bench-rgb · How It Works · Data refreshed daily, snapshot 2026-10-07.