ENC-Bench - Coordinate Localization (Pixel): leaderboard
Metric: Acc@200px accuracy (%): share of ENC-Bench spatial reasoning answers with a marked point located directly in pixel coordinates within 200 pixels of the target, numeric answers on ENC-Bench's 840 NOAA S-57 electronic navigational charts rendered with OpenCPN in day, dusk and night palettes at six scales, zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 21.43 | #145 |
| 2 | Gemini 2.5 Flash | 21.03 | #237 |
| 3 | GLM-4.5V | 14.38 | #339 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 12.9 | #228 (Qwen 3 VL 235B A22B) |
| 5 | Llama 4 Maverick Instruct | 12.9 | #439 |
| 6 | Qwen 3 VL 235B A22B Instruct | 12.2 | #264 |
| 7 | InternVL3-38B | 10.52 | #395 |
| 8 | Qwen 3 VL 32B (Thinking) | 7.34 | #287 (Qwen 3 VL 32B) |
| 9 | GPT-4o | 6.94 | #333 |
| 10 | Qwen 3 VL 32B Instruct | 5.16 | #276 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=enc-bench-coordinate-localization-pixel · How It Works · Data refreshed daily, snapshot 2026-10-11.