Up to four models
GPT-4o vs Qwen2
On the index (GPT-4 = 100), GPT-4o scores 111 and Qwen2 106. 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
11195–127
WeightsClosed
ReleasedMay 2024
Price in / out$2.5 / $10
Context128K
Core tests taken2 of 9
GPT-4o and Qwen2 are too close to call (5 points apart, within the uncertainty), ahead on 2 of 2 shared core tests.
Test by testthird-party results
GPT-4o
Qwen2
Every result as a table
| Test | GPT-4o | Qwen2 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 48.9% | 40.8% |
| MMLU (HELM runs) | 84.2% | 82.4% |
| Maths | ||
| MATH (level 5) | 51.0% | 39.1% |
Task length · METR24 sec
18 sec
Tests at least two of these models have taken. Bold rows are the core tests.