Up to four models
Qwen2.5 vs Llama 3.1
On the index (GPT-4 = 100), Qwen2.5 scores 112 and Llama 3.1 110. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9
Qwen2.5 and Llama 3.1 are too close to call (2 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Qwen2.5 | Llama 3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 49.1% | 50.9% |
| MMLU (HELM runs) | 83.4% | 84.5% |
| Maths | ||
| AIME-style maths (OTIS mock) | 8.1% | 9.7% |
| MATH (level 5) | 63.2% | 49.8% |
| Coding | ||
| WeirdML | 16.0% | 21.4% |
| Agents | ||
| DTBench | 62.9% | 61.4% |
Task length · METR
21 sec
Tests at least two of these models have taken. Bold rows are the core tests.