Data as of September 29, 2026 · How the score is built
Released Mar 10, 2026512K context
Trinity-Large-Thinking
Decision readingTrinity-Large-Thinking scores 34.2 out of 100 and ranks #148 of 209. This profile shows 5 source-displayable benchmark rows; its strongest eligible category is Agentic at #104. API pricing is $0.25 input and $0.9 output per million tokens.
Released Mar 10, 2026 — see all recent releases
Trinity-Large-Thinking will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
34.2/100
field median 50.5#148 of 209 ranked models
Public
#148of 209
Verified —
Price
$0.25input / $0.90 output
input median $1blended $0.57
Speed
317tok/s
field median 93 tok/sFirst token 7.63 s
Context
512Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Agentic ranks #104. Particularly useful for coding agents, browser research, and computer-use workflows.
Validate before choosing
5 published rows leave some tracked benchmark slots empty. Coding is its lowest eligible category at #119.
Source-linked · 5 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #104 of 117Percentile 11thWeight 22%1 benchmarkVerified | 17.6 | 1 benchmark | Verified | |||
| CodingRank #119 of 142Percentile 16thWeight 20%1 benchmarkReported | 21.0 | 1 benchmark | Reported | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #114 of 168Percentile 32ndWeight 12%2 benchmarksReported | 35.9 | 2 benchmarks | Reported | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%1 benchmarkReported | Score pending | 1 benchmark | Reported |
5 of 486 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- Coding0/1 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge0/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math0/1 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Trinity-Large-Thinking category percentile values
- Agentic11th percentile
- Coding16th percentile
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge32nd percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#104/117
- Coding#119/142
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#114/168
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Verified*SWE-bench Verified (mini-swe-agent-v2) | Score63.2% | Versus best verified row | GapNo verified comparator | WeightDisplay only | Secondary exact |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Gert LabsGert Labs Composite Game Benchmark | Score32.55% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap40.4 behind | WeightDisplay only | Benchmark exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQA-DGPQA Diamond | Score76.3% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap19.7 behind | WeightDisplay only | Secondary exact |
| MMLU-Pro (Arcee)MMLU-Pro first-party comparison snapshot | Score83.4% | Versus best verified row Best verified: Trinity-Large-Preview · 75.2% | Gap8.2 behind | WeightDisplay only | Secondary exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME25 (Arcee)AIME25 first-party comparison snapshot | Score96.3% | Versus best verified row Best verified: Trinity-Large-Preview · 24.0% | Gap72.3 behind | WeightDisplay only | Secondary exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 5 rowsWhat it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
Trinity-Large-Thinking · 34.2 score · $0.57 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Thinking
Trinity-Large-PreviewSpec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 512K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Trinity-Large-Thinking ranks #148 of 209 on the public leaderboard with a score of 34.22/100. It does not yet have enough sourced coverage for a verified position.
Trinity-Large-Thinking is a open weight model with a 512K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official exact-value snapshot from Arcee AI's April 1, 2026 Trinity-Large-Thinking launch post. BenchLM stores the published chart values as display-only references so they do not overwrite the core weighted benchmark rows used elsewhere on the site.
Trinity-Large-Thinking sits in the Trinity Large family with Trinity-Large-Preview. 5 of 486 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Agentic at #104, while its lowest eligible position is Coding at #119. particularly useful for coding agents, browser research, and computer-use workflows.
Last updated September 29, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Trinity-Large-Thinking perform overall in AI benchmarks?
Trinity-Large-Thinking ranks #148 out of 209 models on the public BenchAlign leaderboard, with a score of 34.22/100. Its evidence status is Estimated, and this profile shows 5 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Trinity-Large-Thinking good for knowledge and understanding?
Trinity-Large-Thinking ranks #114 out of 168 eligible models for knowledge and understanding, with a public category score of 35.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Trinity-Large-Thinking good for coding and programming?
Trinity-Large-Thinking ranks #119 out of 142 eligible models for coding and programming, with a public category score of 21/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Trinity-Large-Thinking good for mathematics?
Trinity-Large-Thinking has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Trinity-Large-Thinking good for agentic tool use and computer tasks?
Trinity-Large-Thinking ranks #104 out of 117 eligible models for agentic tool use and computer tasks, with a public category score of 17.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Trinity-Large-Thinking open source?
Trinity-Large-Thinking is an open-weight model from Arcee AI. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to Trinity-Large-Thinking?
Trinity-Large-Thinking belongs to the Trinity Large family. Related tracked variants include Trinity-Large-Preview. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Trinity-Large-Thinking have full benchmark coverage on BenchLM?
No. Trinity-Large-Thinking currently has 21 source-displayable rows across 486 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Trinity-Large-Thinking?
Trinity-Large-Thinking has a reported context window of 512K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.