IELTS Writing Score Estimation (With Examples) - RMSE: leaderboard
Metric: RMSE in IELTS band points (0-9), lower is better; predicted writing bands versus reported examiner scores on 400 Task 2 essays, with examples, rubric supplied; two ratings with disagreement retry protocol. Source: aclanthology.org. Saturation forecast: Estimated already saturated. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 1.05 | #335 |
| 2 | Llama 3 70B Instruct | 1.25 | #624 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=ielts-writing-score-estimation-with-examples-rmse · How It Works · Data refreshed daily, snapshot 2026-10-12.