NarrativeWorldBench: leaderboard
Metric: Plot-Beat F1 (h=50) (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 81 |
| 2 | Claude Opus 4.5 (Thinking) | 80 |
| 3 | Gemini 2.5 Pro | 79 |
| 4 | O3 Pro | 79 |
| 5 | DeepSeek R1 | 78 |
| 6 | Grok 4 (High) | 78 |
| 7 | Llama 3.1 405B | 71 |
| 8 | GPT-3.5 Turbo | 54 |
Interactive version: theaggregate.ai/benchmark?slug=narrativeworldbench · How It Works · Data refreshed daily, snapshot 2026-09-05.