AGC-Bench - schnovel: leaderboard
Metric: Dataset z-score. Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5 | 2.04 |
| 2 | Llama 3.2 11B Instruct | 1.91 |
| 3 | Ministral 3 8B | 1.63 |
| 4 | GLM-4.7 | 1.56 |
| 5 | Hermes 4 405B | 1.56 |
| 6 | GLM-5-Turbo | 1.42 |
| 7 | GPT-4o Mini | 1.35 |
| 8 | Qwen Turbo | 1.35 |
| 9 | GPT-4.1 | 1.2 |
| 10 | Gemma 4 31B (IT) | 1.13 |
| 11 | GPT-5.4 | 1.06 |
| 12 | GPT-5.4 Nano | 1.06 |
| 13 | GPT-4o | 0.98 |
| 14 | Nemotron 3 Super | 0.98 |
| 15 | GPT-5.1 | 0.9 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-schnovel · How It Works · Data refreshed daily, snapshot 2026-09-05.