HM-Bench (Report): leaderboard
Metric: Average accuracy (%) over all tasks of HM-Bench's 19,337 hyperspectral multiple-choice questions (2,178 samples, 13 task categories) with report-only input: a structured text report of spectral and spatial statistics computed from the 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 | GPT-5.4 Mini | 37.45 |
| 2 | InternVL3-14B | 37.26 |
| 3 | Claude Sonnet 4.6 | 36.57 |
| 4 | InternVL2-8B | 36.17 |
| 5 | Grok 4 | 31.68 |
| 6 | Qwen 2.5 VL 7B Instruct | 31.03 |
Interactive version: theaggregate.ai/benchmark?slug=hm-bench-report · How It Works · Data refreshed daily, snapshot 2026-10-07.