O3 (2025-04-16) (High): benchmark results
O3 (2025-04-16) evaluated at the high reasoning-effort setting. Provider: OpenAI. Released 2025-04-16. Access: API.
Aggregate Rating 1695 ± 9, rank #375 of 2168 rated models, from 199 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Knowledge - Common Sense (CompassBench 2601) | 95.5 | Score (%) | 100 |
| OpenCompass LLM - Code (CompassBench 2507) | 50.6 | Score (%) | 100 |
| OpenCompass LLM - Code - Chinese (CompassBench 2507) | 50 | Score (%) | 100 |
| OpenCompass LLM - Knowledge - English (CompassBench 2510) | 93.8 | Score (%) | 100 |
| OpenCompass LLM - Language - English (CompassBench 2510) | 89.7 | Score (%) | 100 |
| OpenCompass LLM - Reasoning - Chinese (CompassBench 2507) | 67.7 | Score (%) | 100 |
| OpenCompass Language - Instruction Following - English (CompassBench 2510) | 85.6 | Score (%) | 100 |
| OpenCompass Math - Reasoning Computation - Chinese (CompassBench 2510) | 67.5 | Score (%) | 100 |
| OpenCompass Reasoning - Academic - Chinese (CompassBench 2507) | 40 | Score (%) | 100 |
| OpenCompass Reasoning - Academic - Chinese (CompassBench 2510) | 46.7 | Score (%) | 100 |
| OpenCompass Code - Competition - Chinese (CompassBench 2507) | 71 | Score (%) | 98.1 |
| OpenCompass Knowledge - Humanities - Chinese (CompassBench 2510) | 92 | Score (%) | 98.1 |
Interactive version: theaggregate.ai/model?slug=o3-2025-04-16-high · How It Works · Data refreshed daily, snapshot 2026-10-20.