YALL Nous Leaderboard: leaderboard
Yet Another LLM Leaderboard snapshot for the Nous benchmark suite, aggregating public AGIEval, GPT4All, TruthfulQA, and Bigbench scores for open LLMs.
Metric: Average. Source: huggingface.co. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 162 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Beyonder-4x7B-v3 | 57.55 | #947 |
| 2 | AlphaMonarch-7B | 57.53 | #1014 |
| 3 | BeagSake-7B | 57.53 | #979 |
| 4 | NeuralMonarch-7B | 57.53 | #946 |
| 5 | NeuralBeagle14-7B | 56.9 | #850 |
| 6 | openchat-3.6-8B-20240522 (2024-05-22) | 54.73 | #1090 |
| 7 | NeuralDaredevil-8B-abliterated | 54.71 | #892 |
| 8 | Daredevil-8B-abliterated | 54.26 | #846 |
| 9 | Starling-LM-7B-beta | 54.17 | #1093 |
| 10 | openchat-3.5-0106 | 54.1 | #1130 |
| 11 | Hermes-2-Theta-Llama-3-8B | 53.58 | #1047 |
| 12 | openchat-3.5-1210 | 53.11 | #1004 |
| 13 | Hermes-2-Pro-Llama-3-8B | 52.9 | #1127 |
| 14 | Phi-3 Mini 4K Instruct | 52.74 | #1297 |
| 15 | openchat_3.5 | 52.7 | #1098 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=yall-nous-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.