Models · Compare
Llama 3.3 70B Instruct vs OpenAI o1
Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.
Specs
| Field | A: Llama 3.3 70B Instruct | B: OpenAI o1 |
|---|---|---|
| Released | 2024-12-06 | — |
| Developer | Meta | OpenAI |
| Openness | Source-available | Proprietary |
| License | Llama 3.3 Community License | Proprietary |
| OSI-approved | no | no |
| Data released | no | no |
| Training code | no | no |
| Architecture | dense | unknown |
| Total params | 70B | — |
| Active params | — | — |
| Experts | — | — |
| Context window | 131K | — |
| Attention | gqa | unknown |
| Position enc. | rope-llama3 | unknown |
| Pretraining tokens | 15.0T | — |
| Post-training | sft, dpo, rejection-sampling | rlhf |
| Training hardware | H100 | — |
| $/M input | — | $15.00 |
| $/M output | — | $60.00 |
| Output tok/sec | — | 75.8 |
Benchmarks
Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.
General reasoning
| MMLU | 86.0 2024-12-06 | — |
| MMLU-Pro | — | 84.1 2026-05-21 |
| GPQA-Diamond | 50.5 2024-12-06 | 77.3 2024-12-05 |
Code
| HumanEval | 88.4 2024-12-06 | — |
| LiveCodeBench | — | 67.9 2026-05-21 |
Math
| MATH | — | 97.0 2026-05-21 |
| AIME 2024 | — | 83.3 2024-12-05 |
Context · A
An incremental post-training refresh of the 70B class that approached 405B-class quality on several benchmarks without the deployment cost. The last dense Llama before Llama 4 went MoE.
Context · B
The first publicly available frontier reasoning model. Trained to spend extra inference compute on a "private chain of thought" before answering, setting the template the open community would chase with R1.