EMRB - L2 Signal Processing Methodology: leaderboard
Metric: Accuracy (%). Source: arxiv.org. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 88.7 |
| 2 | Grok 4.5 | 86.4 |
| 3 | GPT-5.5 | 86 |
| 4 | GLM-5.2 | 83.8 |
| 5 | Claude Sonnet 4.6 | 82.6 |
| 6 | Kimi K2.6 | 79.7 |
| 7 | Gemini 3.1 Pro (Preview) | 79.6 |
| 8 | DeepSeek V4 Pro | 77.9 |
| 9 | MiMo-V2.5-Pro | 72 |
| 10 | DeepSeek V4 Flash | 65.1 |
| 11 | MiniMax-M3 | 62.5 |
| 12 | Gemini 3.5 Flash | 46.3 |
| 13 | Llama 3.3 70B | 22.7 |
Interactive version: theaggregate.ai/benchmark?slug=emrb-l2-signal-processing-methodology · How It Works · Data refreshed daily, snapshot 2026-09-19.