AGC-Bench - munch — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 1.18 |
| 2 | GPT-5.5 | 1.18 |
| 3 | GPT-4.1 Mini | 1.06 |
| 4 | GPT-5.4 | 1.04 |
| 5 | Claude Sonnet 4.6 | 0.98 |
| 6 | Claude Opus 4.7 | 0.98 |
| 7 | GPT-5.1 | 0.98 |
| 8 | Gemma 4 31B (IT) | 0.98 |
| 9 | GLM-5.1 | 0.98 |
| 10 | Claude Opus 4.5 | 0.98 |
| 11 | ERNIE 4.5 300B A47B | 0.98 |
| 12 | GPT-5.4 Mini | 0.94 |
| 13 | DeepSeek V3.2 | 0.9 |
| 14 | DeepSeek V3.2 Exp | 0.9 |
| 15 | GLM-4.7 | 0.9 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-munch · How the rankings work · Data refreshed daily, snapshot 2026-07-22.