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. Saturation forecast: Around April 2027. 23 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 1727 | #83 |
| 2 | GPT-5.5 | 1699 | #31 |
| 3 | Claude Opus 4.7 | 1685 | #49 |
| 4 | Gemini 3 Pro (Preview) | 1663 | #66 |
| 5 | Claude Opus 4.1 | 1624 | #140 |
| 6 | Gemini 3 Flash (Preview) | 1608 | #82 |
| 7 | Claude Sonnet 4.5 | 1592 | #142 |
| 8 | Gemini 2.5 Pro | 1585 | #152 |
| 9 | GPT-5.2 | 1521 | #110 |
| 10 | GPT-5 Codex | 1490 | #127 |
| 11 | GPT-4o ChatGPT | 1439 | |
| 12 | GLM-4.7 | 1405 | #192 |
| 13 | Grok 4 | 1349 | #181 |
| 14 | MiniMax-M2.1 | 1343 | #289 |
| 15 | Kimi K2.5 | 1340 | #144 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=asciibench · How It Works · Data refreshed daily, snapshot 2026-10-20.