Up to four models
GPT-4o (Aug 2024) vs GPT-4o (Nov 2024)
On the index (GPT-4 = 100), GPT-4o (Aug 2024) scores 112 and GPT-4o (Nov 2024) 111. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-4o (Aug 2024)
11295–128
WeightsClosed
ReleasedAug 2024
Price in / out$2.5 / $10
Context128K
Core tests taken2 of 9
GPT-4o (Nov 2024)
11194–127
WeightsClosed
ReleasedNov 2024
Price in / out$2.5 / $10
Context128K
Core tests taken3 of 9
GPT-4o (Aug 2024) and GPT-4o (Nov 2024) are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests, at a similar price.
Test by testthird-party results
GPT-4o (Aug 2024)GPT-4o (Nov 2024)
Every result as a table
| Test | GPT-4o (Aug 2024) | GPT-4o (Nov 2024) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 49.2% | 47.9% |
| Maths | ||
| AIME-style maths (OTIS mock) | 6.4% | 6.3% |
| MATH (level 5) | 53.3% | 49.8% |
| FrontierMath (2025 set) | 0.3% | 0.3% |
| Coding | ||
| Aider Polyglot | 23.1% | 18.2% |
Tests at least two of these models have taken. Bold rows are the core tests.