Skip to content
ModelCap

Trinity Large Thinking

Current board #53Arena #172Restricted license

Arcee AI·arcee-ai/trinity-large-thinking

Trinity Large Thinking is a language model published by Arcee AI. 2 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 262K tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · Current board
55.3#53
Measured · 82% support · score interval 55.3–62.1
Market Gravity
32.7
Secondary market signal
Input
$0.22
per 1M tokens
Output
$0.85
per 1M tokens
Context
262K
tokens
Providers
2
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Arcee AICheapest$0.25$0.80262K—100.0%
Parasailfp4$0.22$0.85262Kfp4—

Reported evaluation leads (4)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
collinear-ai/yc-bench
medium
—32,667
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—76.3
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
—63.2
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
—83.4
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
55.3
Measured · 2 public benchmark observations across 2 boards
Current board
#53
Public rank basis
Measured (measured)
Index support
81.9% · strong
Index interval
55.3–62.1
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · arcee-ai/arcee-ai/trinity-large-thinking · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata arcee-ai/Trinity-Large-Thinking@dc6a99b6b74202880e31491a445a94884c97890c (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
58.7
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
58.7
Evidence status
confirmed · 83% mass
General preference
58.7
Coding
58.7
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
82%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
5.5
Liquidity (providers × uptime)
76.4
Open reach (HF downloads)
—
Surface (context / tools / modalities)
75.3
Freshness
61.4
  • · OpenRouter popularity #218
  • · 2 live providers
  • · Catalogue: context 262144, reasoning, tools
  • · First seen 2026-04-01

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
86.0
strong · 98% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
92.5
Deployability
90.0
Evaluation provenance
52.7

Missing: evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
32.7
OpenRouter weekly popularity
#218 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#172 of 385
Rating
1368.7
95% confidence interval
1364–1373
Votes
29K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
5.5

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
76.4

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
61.4

Time since first public availability, on a six-month half-life.

Specification

Context window
262K tokens
Max output
262K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.06 / 1M
First seen on OpenRouter
1 Apr 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Licence
openmdw-1.1
Pinned revision
dc6a99b6b742
Parameters
398.6B
Architecture
AfmoeForCausalLM
Model type
afmoe
Hugging Face downloads (30d)
11K
Downloads (all time)
64K
Likes
186
Repository
arcee-ai/Trinity-Large-Thinking
Repository updated
28 May 2026, 22:45 UTC
Base lineage
arcee-ai/Trinity-Large-Base