Skip to content
aiqbench

Arcee-AI · model passport

Trinity Large Preview

trinity-large-preview
  • Open weights
  • Apache 2.0 licence
  • 398.6B params
  • Released 2026-01-27(HF repo created)
6/27axes covered
Overall · LMArena
1,379#175 of 396
Best percentile
72.4HHEM Hallucination (Vectara)
Cohort standing
51.6median 55.7

What the data says

Benchmarked on 6 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 9.9 pct — Factuality Arena (1,372)

Uneven: 62.5 percentile points between its best and worst axis — 72.4 pct on HHEM Hallucination (Vectara) versus 9.9 pct on Factuality Arena.

  • HHEM Hallucination (Vectara)72.4 pct93.1%Verify →
  • Coding61.6 pct1,443Verify →
  • Hard prompts57.6 pct1,403Verify →
  • Instruction following57.1 pct1,370Verify →
  • Overall56.1 pct1,379Verify →
  • Factuality Arena9.9 pct1,372Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositoryarcee-ai/Trinity-Large-Preview
Parameters398.6B
ArchitectureAfmoeForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "arcee-ai/Trinity-Large-Preview"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • trinity-large-preview stands at 51.6 (raw mean 52.4) — measured on 6 of 27 axes.

    standingtemplateVerify →

  • trinity-large-preview stands at 51.6 versus a cohort median of 55.7 across 112 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →