ENC-Bench - Safety Passage Assessment: leaderboard
Metric: Accuracy (%) on ENC-Bench's 702 safety passage assessment questions (Decision-Making: judging whether a vessel of a given draft can pass safely, true or false; two options), 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 August 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4.5V | 65.67 | #339 |
| 2 | Qwen 3 VL 235B A22B (Thinking) | 61.54 | #228 (Qwen 3 VL 235B A22B) |
| 3 | Qwen 3 VL 235B A22B Instruct | 58.97 | #264 |
| 4 | Qwen 3 VL 32B Instruct | 58.4 | #276 |
| 5 | Gemini 2.5 Pro | 57.55 | #145 |
| 6 | Llama 4 Maverick Instruct | 57.55 | #439 |
| 7 | Qwen 3 VL 32B (Thinking) | 55.98 | #287 (Qwen 3 VL 32B) |
| 8 | Gemini 2.5 Flash | 55.84 | #237 |
| 9 | InternVL3-38B | 54.13 | #395 |
| 10 | GPT-4o | 45.44 | #333 |
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-safety-passage-assessment · How It Works · Data refreshed daily, snapshot 2026-10-11.