NARRA-Gym for Evaluating Interactive Narrative — leaderboard
Metric: StoryQ (self-reported). Source: benchmarklist.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 3.9 |
| 2 | Claude Opus 4.6 | 3.48 |
| 3 | DeepSeek V4 Pro | 3.2 |
| 4 | GPT-5.4 | 3.17 |
| 5 | DeepSeek V3.2 | 3.14 |
| 6 | GLM-5.1 | 2.68 |
| 7 | Gemini 3.1 Pro (Preview) | 2.56 |
| 8 | Qwen 3.5 397B A17B | 2.43 |
Interactive version: theaggregate.ai/benchmark?slug=narra-gym-for-evaluating-interactive-narrative · How the rankings work · Data refreshed daily, snapshot 2026-07-22.