BrainBench (EEG) - BrainAgent - Foundational Analysis: leaderboard
BrainBench (arXiv 2608.04156v2, Table 1) score on the Foundational Analysis subset of core EEG processing and analysis tasks, with each model running through the structured BrainAgent tool workflow in an isolated container and its report and artifacts checked by task validators. 0-100; higher is better. Optional reasoning modes disabled.
Metric: EEG analysis score (0-100). Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 81.47 | #16 |
| 2 | GPT-5.6 Sol (Non-reasoning) | 77.86 | #22 (GPT-5.6 Sol) |
| 3 | Qwen 3.7 Plus (Non-reasoning) | 73.08 | #98 (Qwen 3.7 Plus) |
| 4 | Kimi K2.5 (Non-reasoning) | 72.36 | #152 (Kimi K2.5) |
| 5 | Qwen 3.7 Max (Non-reasoning) | 72.21 | #85 (Qwen 3.7 Max) |
| 6 | GPT-5.6 Terra (Non-reasoning) | 69.48 | #40 (GPT-5.6 Terra) |
| 7 | GLM-5 (Non-reasoning) | 68.92 | #149 (GLM-5) |
| 8 | MiniMax-M2.5 | 68.51 | #316 |
| 9 | DeepSeek V4 Flash (Non-reasoning) | 67.38 | #155 (DeepSeek V4 Flash) |
| 10 | GPT-5.6 Luna (Non-reasoning) | 65.2 | #79 (GPT-5.6 Luna) |
| 11 | Qwen 3.5 122B A10B (Non-reasoning) | 63.12 | #184 (Qwen 3.5 122B A10B) |
| 12 | Qwen 3.5 35B A3B (Non-reasoning) | 59.98 | #268 (Qwen 3.5 35B A3B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=brainbench-eeg-brainagent-foundational-analysis · How It Works · Data refreshed daily, snapshot 2026-11-05.