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.
Aggregate Rating 1637 ± 5, rank #336 of 1656 rated models, from 1292 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AutoLogi | 62.04 | Score (imported) | 100 |
| CG-Bench - Accuracy@IoU | 4.33 | Accuracy@IoU (%) | 100 |
| CG-Bench - Clue Grounding mIoU | 5.73 | Temporal Grounding mIoU (%) | 100 |
| CG-Bench - Open-Ended | 39.2 | Open-Ended Accuracy (%) | 100 |
| CRMArena - BRI (Function Calling Native) | 59.2 | Exact match (%) | 100 |
| CRMArena - HTU (Function Calling Native) | 47.7 | Exact match (%) | 100 |
| CRMArena - MTA (Act) | 29.2 | Exact match (%) | 100 |
| CRMArena - MTA (Function Calling Native) | 27.7 | Exact match (%) | 100 |
| CRMArena - NCR (Function Calling Native) | 60 | Exact match (%) | 100 |
| CRMArena - Overall (Function Calling Native) | 54.4 | Mean task score (%) | 100 |
| CRMArena - TII (Act) | 68.5 | Exact match (%) | 100 |
| CRMArena - TII (Function Calling Native) | 97.7 | Exact match (%) | 100 |
Interactive version: theaggregate.ai/model?slug=gpt-4o-2024-08-06 · How It Works · Data refreshed daily, snapshot 2026-10-20.