AGC-Bench - mops — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Medium 3.1 | 2.56 |
| 2 | Llama 3 8B Instruct | 2.05 |
| 3 | Ministral 3 8B | 1.99 |
| 4 | Claude Sonnet 4.6 | 1.68 |
| 5 | nemotron-3-super-120B-a12B | 1.53 |
| 6 | Mistral Large 3 | 1.46 |
| 7 | Llama 3.1 70B Instruct | 1.32 |
| 8 | Gemma 3 4B (IT) | 1.08 |
| 9 | nova-2-lite-v1 | 1.05 |
| 10 | Claude Opus 4.6 | 1.02 |
| 11 | DeepSeek V3 (0324) | 1.01 |
| 12 | Claude Opus 4.7 | 1 |
| 13 | Kimi K2 0905 | 1 |
| 14 | GPT-5.1 | 0.96 |
| 15 | GPT-5.4 Nano | 0.81 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-mops · How the rankings work · Data refreshed daily, snapshot 2026-07-22.