AGC-Bench - thenextchapter — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2 0905 | 2.77 |
| 2 | Qwen 3 Next 80B A3B Instruct | 2.37 |
| 3 | Mistral Medium 3.1 | 2.08 |
| 4 | Ministral 3 8B | 1.72 |
| 5 | Kimi K2.6 | 1.38 |
| 6 | GPT-5.1 | 1.25 |
| 7 | Kimi K2.5 | 1.24 |
| 8 | nemotron-3-nano-30B-a3B | 1.19 |
| 9 | Mistral Large 3 | 1.13 |
| 10 | DeepSeek V3.1 Terminus | 0.94 |
| 11 | DeepSeek V3.1 | 0.94 |
| 12 | GPT-5.4 Nano | 0.93 |
| 13 | DeepSeek V3.2 Exp | 0.84 |
| 14 | Gemma 3 27B (IT) | 0.77 |
| 15 | nemotron-3-super-120B-a12B | 0.76 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-thenextchapter · How the rankings work · Data refreshed daily, snapshot 2026-07-22.