AGC-Bench - historical_analogy — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 81 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-4.7 | 1.94 |
| 2 | GLM-5-Turbo | 1.94 |
| 3 | Claude Opus 4.7 | 1.84 |
| 4 | GPT-4o | 1.58 |
| 5 | Kimi K2.5 | 1.58 |
| 6 | GLM-5.1 | 1.48 |
| 7 | Kimi K2.6 | 1.41 |
| 8 | Hermes 4 70B | 1.41 |
| 9 | Hermes 4 405B | 1.41 |
| 10 | DeepSeek V3.2 Exp | 1.38 |
| 11 | DeepSeek V3.1 | 1.31 |
| 12 | Gemma 4 31B (IT) | 1.23 |
| 13 | GPT-4.1 | 1.11 |
| 14 | Gemma 4 26B A4B (IT) | 1.05 |
| 15 | Hunyuan A13B-Instruct | 1.05 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-historical-analogy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.