All comparisons
Google-Proof Q&A 44.8 — HellaSwag 91.1 — HumanEval 68.2 — Massive Multitask Language Understanding 76.9 — Instruction-Following Evaluation 59.5 — MMLU PRO 40.5 —
Llama 3 8B Instruct vs Trinity-Large-Preview
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2024-04-18 | 2026-01-27 |
| Context window | 8K | 128K |
| Parameters | 8B | 400B |
| Architecture | decoder only | Sparse Mixture of Experts (MoE) |
| License | Open Source | Apache 2.0 |
| Knowledge cutoff | — | — |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks