Up to four models
Qwen3-8B vs DeepSeek-R1-Distill-Llama-70B
On the index (GPT-4 = 100), Qwen3-8B scores 126 and DeepSeek-R1-Distill-Llama-70B 125. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
125109–142
WeightsOpen
ReleasedJan 2025
Price in / out–
Context–
Core tests taken1 of 9
Qwen3-8B and DeepSeek-R1-Distill-Llama-70B are too close to call (0 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Qwen3-8B | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 56.8% | 55.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 56.1% | 51.4% |
Tests at least two of these models have taken. Bold rows are the core tests.