Data as of November 13, 2026 · How the score is built
Trinity-Large-Thinking
- Released Mar 10, 2026
- 512K context
Decision readingTrinity-Large-Thinking scores 43.2 out of 100 and ranks #133 of 215. This profile shows 8 source-displayable benchmark rows; its strongest eligible category is Agentic at #117. API pricing is $0.25 input and $0.9 output per million tokens.
Email me when its price, rank or availability changes.
Capability
43.2/100
field median 49.4#133 of 215 ranked models
Public
#133of 215
Verified —
Price
$0.25input / $0.90 output
input median $0.60blended $0.57
Speed
367tok/s
field median 92 tok/sFirst token 6.63 s
Context
512Ktokens
field median 256,000Reported for this model; direct source link not stored
Decision snapshot
Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.
Strongest published evidence
Agentic ranks #117. Particularly useful for coding agents, browser research, and computer-use workflows.
Validate before choosing
8 published rows leave some tracked benchmark slots empty. Instruction Following is its lowest eligible category at #140.
Source-linked · 8 displayable benchmark rows
Is Trinity-Large-Thinking right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Where Trinity-Large-Thinking ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category 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 #117 of 135Percentile 13thWeight 22%2 benchmarksVerified | 22.7 | 2 benchmarks | Verified | |||
| CodingRank #138 of 162Percentile 15thWeight 20%1 benchmarkReported | 18.6 | 1 benchmark | Reported | |||
| ReasoningRank #121 of 160Percentile 25thWeight 17%Not listedUnlisted sources | 30.2 | Not listed | Unlisted sources | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #129 of 180Percentile 28thWeight 12%2 benchmarksReported | 36.9 | 2 benchmarks | Reported | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #140 of 157Percentile 11thWeight 5%1 benchmarkVerified | 28.9 | 1 benchmark | Verified | |||
| MathWeight 5%1 benchmarkReported | Score pending | 1 benchmark | Reported |
8 of 917 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.
- Agentic2/2 verified
- Coding0/1 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge0/2 verified
- MultilingualNot measured
- Inst. Following1/1 verified
- 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
- Agentic13th percentile
- Coding15th percentile
- Reasoning25th percentile
- MultimodalNot eligible
- Knowledge28th percentile
- MultilingualNot eligible
- Instruction following11th percentile
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#117/135
- Coding#138/162
- Reasoning#121/160
- MultimodalNot ranked
- Knowledge#129/180
- MultilingualNot ranked
- Inst. Following#140/157
- MathNot ranked
Benchmark ledger
Every result says who ran the test. For this model, Arcee AI ran 2 of 8. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| SWE-bench Verified*SWE-bench Verified (mini-swe-agent-v2) | 63.2% | GapNo verified comparator | Another lab’s comparison table | Shown only |
Agentic2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| τ²-bench Airlineτ²-Bench Airline Domain | 88.0% | Best verified: Trinity-Large-Thinking · 88.0% | GapHighest listed | Reported by Arcee AI | Shown only |
| Gert LabsGert Labs Composite Game Benchmark | 32.55% | Best verified: Claude Opus 4.8 · 72.97% | Gap40.4 behind | Run by Gert Labs | Shown only |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| GPQA-DGPQA Diamond | 76.3% | Best verified: GPT-6 Astra · 96.0% | Gap19.7 behind | Another lab’s comparison table | Shown only |
| MMLU-Pro (Arcee)MMLU-Pro first-party comparison snapshot | 83.4% | Best verified: Trinity-Large-Preview · 75.2% | Gap8.2 behind | Another lab’s comparison table | Shown only |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | 52.3% | Best verified: Flint · 89.2% | Gap36.9 behind | Reported by Arcee AI | CountsWeighted 70% |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| AIME25 (Arcee)AIME25 first-party comparison snapshot | 96.3% | Best verified: Trinity-Large-Preview · 24.0% | Gap72.3 behind | Another lab’s comparison table | Shown only |
External signals1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| NYT ConnectionsNYT Connections LLM Benchmark (extended version) | 16.5% | Best verified: Gemini 4 Carbon · 99.3% | Gap82.8 behind | Run by NYT Connections | Shown only |
Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.
What 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 · 43.2 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
- textTrinity-Large-Thinking model card
- Output modalities
- textTrinity-Large-Thinking model card
- 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
- Trinity-Large-Thinking needs ~320GB VRAM (4× NVIDIA H100 (80GB)).
- 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 #133 of 215 on the public leaderboard with a score of 43.24/100. 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. 8 of 917 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Agentic at #117, while its lowest eligible position is Instruction Following at #140. particularly useful for coding agents, browser research, and computer-use workflows.
Last updated November 13, 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.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does Trinity-Large-Thinking perform overall in AI benchmarks?
Trinity-Large-Thinking ranks #133 out of 215 models on the public BenchAlign leaderboard, with a score of 43.24/100. Its evidence status is Estimated, and this profile shows 8 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 #129 out of 180 eligible models for knowledge and understanding, with a public category score of 36.9/100. 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 #138 out of 162 eligible models for coding and programming, with a public category score of 18.6/100. 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 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 #117 out of 135 eligible models for agentic tool use and computer tasks, with a public category score of 22.7/100. 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 instruction following?
Trinity-Large-Thinking ranks #140 out of 157 eligible models for instruction following, with a public category score of 28.9/100. 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 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 19 source-displayable rows. 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.