Skip to content
aiqbench

Arcee · model passport

Arcee AI: Trinity Large Thinking

trinity-large-thinking
  • Open weights
  • Apache 2.0 licence
  • 398.6B params
  • 262,144 context
  • Released 2026-04-01(HF repo created)
7/27axes covered
Overall · LMArena
1,367#183 of 396
Best percentile
64.2IFBench (Artificial Analysis)
Cohort standing
44.8median 62.8

What the data says

Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 9.3 pct — Factuality Arena (1,371)
  • 9.4 pct — WebDev Arena (1,238)

Uneven: 54.9 percentile points between its best and worst axis — 64.2 pct on IFBench (Artificial Analysis) versus 9.3 pct on Factuality Arena.

  • IFBench (Artificial Analysis)64.2 pct56.3%Verify →
  • Hard prompts54.3 pct1,385Verify →
  • Overall54 pct1,367Verify →
  • Instruction following54 pct1,359Verify →
  • Coding53.2 pct1,413Verify →
  • WebDev Arena9.4 pct1,238Verify →
  • Factuality Arena9.3 pct1,371Verify →
  • 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
  • HHEM Hallucination (Vectara)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-Thinking
Parameters398.6B
ArchitectureAfmoeForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "arcee-ai/Trinity-Large-Thinking"
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 →

Use it hosted

API model IDarcee-ai/trinity-large-thinking
Context length262,144 tokens
Max output80,000 tokens
Input price$0.25 per 1M tokens
Cached input price$0.06 per 1M tokens
Output price$0.80 per 1M tokens

API parameters this endpoint supports

Include reasoningMax tokensReasoningTemperatureTool choiceTool callingTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"arcee-ai/trinity-large-thinking","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

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-thinking stands at 44.8 (raw mean 42.6) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • trinity-large-thinking stands at 44.8 versus a cohort median of 62.8 across 116 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 →