Record Test rt-v1.1 - Text - Speaker Name Accuracy: leaderboard
Record Test rt-v1.1 - Text - Speaker Name Accuracy. Exploratory: two fresh repetitions per model (reps 2-3 headline); failed draws stay in the denominator; no confidence intervals. Metric: Speaker Name Accuracy (%). Higher is better.
Metric: Speaker Name Accuracy (%). Source: heydonna.law. Saturation forecast: Around February 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 52.52 | #10 |
| 2 | Claude Sonnet 5.5 | 48.12 | #19 |
| 3 | Claude Haiku 5.5 | 41.12 | #65 |
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-text-speaker-name-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-13.