Record Test rt-v1.1 - Audio - Word Preservation: leaderboard
Record Test rt-v1.1 - Audio - Word Preservation. Exploratory: two fresh repetitions per model (reps 2-3 headline); failed draws stay in the denominator; no confidence intervals. Metric: Word Preservation (%). Higher is better.
Metric: Word Preservation (%). Source: heydonna.law. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon (Low) | 99.41 | #11 (Gemini 4 Argon) |
| 2 | Gemini 3.8 Flash (Low) | 98.97 | #36 (Gemini 3.8 Flash) |
| 3 | Gemini 3.1 Flash Lite (Minimal) | 97.43 | #364 (Gemini 3.1 Flash Lite) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=record-test-rt-v1-1-audio-word-preservation · How It Works · Data refreshed daily, snapshot 2026-11-13.