TextQuests (With Clues): leaderboard
Playing 25 classic Infocom interactive-fiction games with the official hint books available: average game completion, testing how well models exploit in-context guidance over long horizons.
Metric: Avg Game Progress (%). Source: www.textquests.ai. Saturation forecast: Around January 2027. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 94 | #6 |
| 2 | GPT-5.6 Sol | 86.84 | #19 |
| 3 | Claude Fable 5 | 82.04 | #16 |
| 4 | GPT-5.5 | 81.68 | #31 |
| 5 | Gemini 3.1 Pro (Preview) | 71.08 | #58 |
| 6 | Gemini 3 Pro | 70.8 | #80 |
| 7 | GPT-5 | 70 | #98 |
| 8 | Claude Opus 4.1 | 68 | #140 |
| 9 | Claude Opus 4.8 | 64.12 | #37 |
| 10 | GPT-5.6 Luna | 63.4 | #68 |
| 11 | GPT-5.6 Terra | 63 | #41 |
| 12 | Gemini 3.5 Flash | 62.16 | #60 |
| 13 | Grok 4 | 61.4 | #181 |
| 14 | Gemini 2.5 Pro | 60.6 | #152 |
| 15 | Claude Opus 4 | 60.5 | #163 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=textquests-with-clues · How It Works · Data refreshed daily, snapshot 2026-10-20.