All comparisons
HellaSwag — 95.7 HumanEval — 85.5 Massive Multitask Language Understanding — 88.5
GPT-4o (08-06) vs DeepSeek V3
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2024-08-06 | 2024-12-26 |
| Context window | 128K | — |
| Parameters | 1.76T (8x222B MoE)* | — |
| Architecture | mixture of experts | mixture of experts |
| License | Proprietary | Unknown |
| Knowledge cutoff | 2023-10 | — |
Capabilities | ||
| Multimodal | ||
| Function calling | ||
| Tool use | ||
| JSON mode | ||
Availability | ||
| Providers | ||
Benchmarks