Up to four models
GPT-3.5 Turbo (Jun 2023) vs Qwen2.5-7B
On the index (GPT-4 = 100), GPT-3.5 Turbo (Jun 2023) scores 97 and Qwen2.5-7B 96. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-3.5 Turbo (Jun 2023)
9781–113
WeightsClosed
ReleasedJun 2023
Price in / out–
Context–
Core tests taken0 of 9
GPT-3.5 Turbo (Jun 2023) and Qwen2.5-7B are too close to call (1 point apart, within the uncertainty).
Test by testthird-party results
GPT-3.5 Turbo (Jun 2023)
Qwen2.5-7B
Every result as a table
| Test | GPT-3.5 Turbo (Jun 2023) | Qwen2.5-7B |
|---|---|---|
| Reasoning & knowledge | ||
| MMLU (HELM runs) | 68.9% | 72.9% |
Tests at least two of these models have taken. Bold rows are the core tests.