Land or Water? (Open Models, 10° Reference) - Accuracy: leaderboard
Metric: Accuracy (%). Source: github.com. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B MXFP4 (Non-reasoning) | 70.83 |
| 2 | Gemma 4 26B A4B (IT) (Q8_0) (Non-reasoning) | 63.89 |
| 3 | Qwen 3.5 9B (Q8_0) (Non-reasoning) | 58.64 |
| 4 | Qwen 2.5 7B Instruct (Q8_0) | 47.38 |
Interactive version: theaggregate.ai/benchmark?slug=land-or-water-open-models-10-reference-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-09.