MMErroR - Error Type Classification - Earth & Environment: leaderboard
Metric: Error Type Classification Accuracy (%). Source: arxiv.org. Saturation forecast: Around December 2026. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 | 66.67 |
| 2 | Seed 2.0 Pro | 66.16 |
| 3 | Gemini 3 Pro (Preview) | 65.39 |
| 4 | GPT-5.2 (xHigh) | 65.14 |
| 5 | Qwen 3 VL 32B (Thinking) | 60.81 |
| 6 | Grok 4 | 59.29 |
| 7 | Claude Opus 4.5 | 56.74 |
| 8 | GLM-4.6V | 52.16 |
| 9 | Qwen 3 VL 32B Instruct | 36.64 |
| 10 | Llama 4 Maverick Instruct | 28.5 |
| 11 | Llama 4 Scout Instruct | 28.24 |
Interactive version: theaggregate.ai/benchmark?slug=mmerror-error-type-classification-earth-environment · How It Works · Data refreshed daily, snapshot 2026-09-25.