GPT-5 (2025-08-07) (High) — benchmark results
Provider: OpenAI. Released 2025-08-07. Access: API.
Unified ELO 1801 ± 45, rank #165 of 1806 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI MATH 500 | 96 | Accuracy (%) | 95.7 |
| Vals AI CaseLaw v2 | 66.45 | Accuracy (%) | 89 |
| MedCode | 49.63 | Score (self-reported) | 82.3 |
| Vals AI MGSM | 92.84 | Accuracy (%) | 78.5 |
| MedScribe | 83.65 | Score (self-reported) | 75 |
| Vals AI IOI | 20 | Accuracy (%) | 58.3 |
| Vals AI Finance Agent | 52.15 | Accuracy (%) | 45.8 |
| Vals AI ProofBench | 18 | Accuracy (%) | 42.4 |
Interactive version: theaggregate.ai/model?slug=gpt-5-2025-08-07-high · How It Works · Data refreshed daily, snapshot 2026-08-07.