GPT-4o (2024-08-06) — benchmark results
August 6, 2024 GPT-4o snapshot, tracked when sources report the dated API model. Provider: OpenAI. Released 2024-08-06. Access: API.
Unified ELO 1616 ± 12, rank #441 of 1776 rated models, from 200 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AutoLogi | 62.04 | Score (self-reported) | 100 |
| HELMET (128K) | 64.8 | Average Score | 100 |
| LiveBench Connections | 58 | Score | 100 |
| LongProc | 94.8 | Accuracy @ 0.5K (%) | 100 |
| Open Portuguese LLM - HateBR Offensive | 93.2 | F1 (%) | 100 |
| OpenVLM Video - MMBench-Video | 43 | Normalized Score (%) | 100 |
| ReliableMath - Prudence | 1.5 | Score (%) | 100 |
| HELM (Stanford) | 92.76 | Mean Win Rate (%) | 98.9 |
| VNTL Leaderboard | 74.97 | Accuracy (%) | 98.8 |
| LiveBench Coding Completion | 55.26 | Score | 98.6 |
| BenchBench | 96.53 | Aggregate Score (%) | 98.5 |
| HELM NaturalQuestions (Closed) | 49.58 | F1 (%) | 97.8 |
Interactive version: theaggregate.ai/model?slug=gpt-4o-2024-08-06 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.