LithoBench - Identification and Description (MCQ): leaderboard
Metric: Accuracy (%) on the 800 multiple-choice identification-and-description questions of LithoBench: pick the lithology of a GF-2 remote-sensing image patch among visually similar distractor categories (an unparsable answer counts as wrong); temperature 0, 1,024 output tokens; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 9B | 92.5 |
| 2 | Gemini 3 Pro | 77.62 |
| 3 | GLM-4.6V | 76.25 |
| 4 | Kimi K2.5 | 75.88 |
| 5 | Grok 4 | 67 |
| 6 | GPT-5.4 | 66.5 |
| 7 | Qwen 3.5 397B A17B | 65.38 |
| 8 | Claude Sonnet 4.6 | 56.25 |
| 9 | Qwen 3.5 27B | 43.13 |
Interactive version: theaggregate.ai/benchmark?slug=lithobench-identification-and-description-mcq · How It Works · Data refreshed daily, snapshot 2026-10-07.