BrainBench (EEG) - BrainAgent - Foundational Analysis: leaderboard
Metric: EEG analysis score (0-100). Source: arxiv.org. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 81.47 |
| 2 | GPT-5.6 Sol (Non-reasoning) | 77.86 |
| 3 | Qwen 3.7 Plus (Non-reasoning) | 73.08 |
| 4 | Kimi K2.5 (Non-reasoning) | 72.36 |
| 5 | Qwen 3.7 Max (Non-reasoning) | 72.21 |
| 6 | GPT-5.6 Terra (Non-reasoning) | 69.48 |
| 7 | GLM-5 (Non-reasoning) | 68.92 |
| 8 | MiniMax-M2.5 | 68.51 |
| 9 | DeepSeek V4 Flash (Non-reasoning) | 67.38 |
| 10 | GPT-5.6 Luna (Non-reasoning) | 65.2 |
| 11 | Qwen 3.5 122B A10B (Non-reasoning) | 63.12 |
| 12 | Qwen 3.5 35B A3B (Non-reasoning) | 59.98 |
Interactive version: theaggregate.ai/benchmark?slug=brainbench-eeg-brainagent-foundational-analysis · How It Works · Data refreshed daily, snapshot 2026-09-19.