ASCIIBench — leaderboard
A/B voting platform for AI-generated ASCII art. Models compete head-to-head and are ranked by ELO rating. Tests creative visual generation constrained to text characters.
Metric: ELO Rating. Source: www.asciibench.com. Status: saturation imminent. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 1701 |
| 2 | GPT-5.5 | 1678 |
| 3 | Gemini 3 Flash (Preview) | 1629 |
| 4 | Gemini 3 Pro (Preview) | 1627 |
| 5 | Claude Sonnet 4.5 | 1621 |
| 6 | Gemini 2.5 Pro | 1620 |
| 7 | Claude Opus 4.5 | 1615 |
| 8 | Claude Opus 4.1 | 1603 |
| 9 | GPT-5.2 | 1552 |
| 10 | GPT-4o ChatGPT | 1489 |
| 11 | GPT-5 Codex | 1461 |
| 12 | GLM-4.7 | 1387 |
| 13 | Kimi K2.5 | 1371 |
| 14 | Grok 4 | 1334 |
| 15 | Grok 4 Fast | 1322 |
Interactive version: theaggregate.ai/benchmark?slug=asciibench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.