TextQuests (No Clues): leaderboard
Playing 25 classic Infocom interactive-fiction games (Zork etc.) without hints: average game completion via long-horizon exploration, puzzle solving and state tracking in a text world.
Metric: Avg Game Progress (%). Source: www.textquests.ai. Saturation forecast: Around March 2027. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 74.24 | #6 |
| 2 | Claude Fable 5 | 54.48 | #16 |
| 3 | GPT-5.6 Sol | 51.48 | #19 |
| 4 | GPT-5.5 | 48.88 | #31 |
| 5 | Gemini 3.1 Pro (Preview) | 45.76 | #58 |
| 6 | Gemini 3 Pro | 41.04 | #80 |
| 7 | Claude Opus 4.8 | 40.08 | #37 |
| 8 | GPT-5.6 Terra | 37.92 | #41 |
| 9 | GPT-5 | 37.8 | #98 |
| 10 | Gemini 3.5 Flash | 35.72 | #60 |
| 11 | Claude Opus 4.1 | 33.9 | #140 |
| 12 | Grok 4 | 31.2 | #181 |
| 13 | O3 | 30.9 | #124 |
| 14 | GPT-5.6 Luna | 30.76 | #68 |
| 15 | GPT-5.4 Mini | 29.6 | #212 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=textquests-no-clues · How It Works · Data refreshed daily, snapshot 2026-10-20.