EMRB - L3 Communication Theory: leaderboard
Metric: Accuracy (%). Source: arxiv.org. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 93.2 |
| 2 | Grok 4.5 | 92.3 |
| 3 | Claude Opus 4.7 | 88.3 |
| 4 | Claude Sonnet 4.6 | 80.2 |
| 5 | GLM-5.2 | 73.7 |
| 6 | DeepSeek V4 Pro | 72.8 |
| 7 | Gemini 3.5 Flash | 72.6 |
| 8 | MiniMax-M3 | 71.2 |
| 9 | DeepSeek V4 Flash | 67.5 |
| 10 | MiMo-V2.5-Pro | 59.4 |
| 11 | Gemini 3.1 Pro (Preview) | 57.8 |
| 12 | Kimi K2.6 | 48.6 |
| 13 | Llama 3.3 70B | 31.2 |
Interactive version: theaggregate.ai/benchmark?slug=emrb-l3-communication-theory · How It Works · Data refreshed daily, snapshot 2026-09-19.