GPT-4o ChatGPT (2025-03-27): benchmark results
Provider: OpenAI. Released 2025-03-27. Access: API.
Aggregate Rating 1701 ± 27, rank #340 of 10916 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BuzzBench (Humour) | 69.11 | Humour Score (0-100) | 96 |
| Creative Writing v3 | 1482.7 | Elo score (imported) | 66.4 |
| EQ-Bench | 1386.5 | Normalized Elo (imported) | 56.4 |
| EQ-Bench Longform Writing | 60.2 | Writing Score (0-100) | 53.2 |
Interactive version: theaggregate.ai/model?slug=gpt-4o-chatgpt-2025-03-27 · How It Works · Data refreshed daily, snapshot 2026-11-08.