LLM ReferenceLLM Reference
All comparisons

Trinity-Large-Thinking vs DeepSeek V3

Side-by-side comparison of specifications, capabilities, and pricing.

Released2026-04-012024-12-26
Context window256K64k
Parameters400B671B
ArchitectureSparse Mixture of Experts (MoE)mixture of experts
LicenseApache 2.0Open Source
Knowledge cutoff2024-04

Capabilities

Vision
Multimodal
Reasoning
Function calling
Tool use
Structured Outputs
Code execution

Availability

Providers

Benchmarks

HellaSwag—95.7HumanEval—85.5Massive Multitask Language Understanding—88.5LiveCodeBench—49.6Aider Polyglot—48.4BigCodeBench—50.0Chatbot Arena—1302.0MMLU PRO—75.9