Up to four models
o1 vs Llama 3.3 70B
On the index (GPT-4 = 100), o1 scores 136 and Llama 3.3 70B 108. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
10892–124
WeightsOpen
ReleasedDec 2024
Price in / out$0.71 / $0.71
Context131K
Core tests taken1 of 9
o1 leads Llama 3.3 70B by 28 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
o1
Llama 3.3 70B
Every result as a table
| Test | o1 | Llama 3.3 70B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 76.8% | 47.4% |
| Fiction.LiveBench | 83.3% | 33.3% |
| SimpleBench | 40.1% | 19.9% |
| Maths | ||
| AIME-style maths (OTIS mock) | 73.3% | 5.1% |
| MATH (level 5) | 94.7% | 41.6% |
| Coding | ||
| WeirdML | 46.1% | 14.4% |
| Agents | ||
| DTBench | 74.7% | 59.5% |
| LMCA | 22.3% | 17.5% |
Task length · METR31 sec
Tests at least two of these models have taken. Bold rows are the core tests.