Skip to content

Trinity-Large-Thinking

Arcee AIOpen weightsReasoningProvisionalReleased Mar 10, 2026Input: text
Compare with ZAYA1-8BSource scores ↗OpenRouter ↗
Overall score
34.5
Rank 163 of 222 · 24.8–44.2
Context window
512K
512,000 tokens
Price per 1M tokens
$0.25 in · $0.90 out
Source: BenchLM
Blended price
$0.41
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Reasoning51.1
  2. 2Knowledge45.0
  3. 3Instruction following#13228.9
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (7)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Agentic & tool use

Gert Labs32.55#47 of 52
τ²-bench Airline88.0#1 of 4

Coding

SWE-bench Verified*63.2#5 of 5

Multimodal

Design Arena Website1137#75 of 91

Knowledge

MMLU-Pro (Arcee)83.4#4 of 5

Instruction following

IFBench52.3#38 of 42

Math

AIME25 (Arcee)96.3#2 of 5

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (BenchLM)$0.25$0.90—
OpenRouter arcee-ai/trinity-large-thinking$0.25$0.80$0.060

Arcee's public pricing page lists Trinity-Large-Thinking at $0.25 input / $0.90 output per million tokens.

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text1340#212 · 30.3K votes
WebDev (coding)1238#139 · 1.4K votes

Open weights

From the Hugging Face repository.

Parameters
399B
Licence
other
Downloads (30 days)
2.3K

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Similar score