LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Trinity Large Thinking vs R1 0528

Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Trinity Large Thinking Replace R1 0528
Trinity Large ThinkingArcee AI
Coding
5.4
Overall
10.8
Output $/M
$0.80
3
R1 0528DeepSeek
Coding
71.4
Overall
13.1
Output $/M
$2.15
38
vs boards won of 42 shared, 1 tied

Decision reading

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 5.4 for Trinity Large Thinking.

Pick Trinity Large Thinking when output tokens cost 2.7x less, or when the context window is larger, 262K against 164K tokens.

Model ATrinity Large ThinkingArcee AI5.4/1001 independent benchmarkNo cost per solved taskModel BR1 0528DeepSeek71.4/1001 independent benchmarkNo cost per solved task
Shared results
42
Trinity Large Thinking only
10
R1 0528 only
17
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Trinity Large Thinking 5.4 from 1 benchmark, R1 0528 71.4 from 1 benchmark.
Widest category
Agentic work, 53.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Trinity Large Thinking 90.1% against R1 0528 36.5%, 53.5 points apart on a 0 to 100 scale.
Output price
Trinity Large Thinking $0.80 against R1 0528 $2.15 per million output tokens, 2.7x apart.
Context window
Trinity Large Thinking takes 262K tokens, R1 0528 164K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryTrinity Large ThinkingBarsR1 0528Ties
Coding12
Intelligence01
Agentic work10
Reasoning041 tie
Math02
Knowledge04
Web design07
General118
All shared boards3381 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index12
Coding benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
Aider polyglotNot measured71.4%Only R1 0528 measured
LMArena WebDev1238Not measuredOnly Trinity Large Thinking measured
AA Coding Index25.8Not measuredOnly Trinity Large Thinking measured
LiveCodeBench (Artificial Analysis run)Not measured77.0%Only R1 0528 measured
SciCode40.6%Not measuredOnly Trinity Large Thinking measured
Terminal-Bench Hard (Artificial Analysis run)22.7%15.9%Trinity Large Thinking
WeirdMLNot measured41.6%Only R1 0528 measured
ALE-BenchNot measured804.1Only R1 0528 measured
LMArena Text: coding13571427R1 0528
LMArena Text: software and IT13621435R1 0528
LMArena WebDev: React1231Not measuredOnly Trinity Large Thinking measured
LMArena WebDev: HTML1240Not measuredOnly Trinity Large Thinking measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
AA Intelligence Index10.813.1R1 0528
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
AA Agentic Index1.0Not measuredOnly Trinity Large Thinking measured
τ²-Bench Telecom90.1%36.5%Trinity Large Thinking
METR time horizonsNot measured53.8%Only R1 0528 measured
DeepResearch BenchNot measured35.1%Only R1 0528 measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
GPQA Diamond (Artificial Analysis run)75.2%81.3%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%15.8%Tie
GPQA Diamond (Epoch AI run)Not measured76.3%Only R1 0528 measured
ARC-AGINot measured21.2%Only R1 0528 measured
ARC-AGI-2Not measured1.1%Only R1 0528 measured
SimpleBenchNot measured40.8%Only R1 0528 measured
LMArena Text: hard prompts13421415R1 0528
LMArena Text: expert13591394R1 0528
LMArena Text: hard prompts in English13561422R1 0528
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
AA Math IndexNot measured76.0Only R1 0528 measured
AIME 2025 (Artificial Analysis run)Not measured76.0%Only R1 0528 measured
OTIS Mock AIMENot measured66.4%Only R1 0528 measured
MATH level 5Not measured96.6%Only R1 0528 measured
LMArena Text: math13651400R1 0528
LMArena Text: mathematical work13501415R1 0528
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
CaseLaw (Vals AI)57.9%Not measuredOnly Trinity Large Thinking measured
CorpFin (Vals AI)54.7%Not measuredOnly Trinity Large Thinking measured
MMLU Pro (Artificial Analysis run)Not measured84.9%Only R1 0528 measured
LMArena Text: science13551430R1 0528
LMArena Text: medicine and healthcare13491445R1 0528
LMArena Text: legal and government13451419R1 0528
LMArena Text: business and finance13291402R1 0528
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
Design Arena: websites11371149R1 0528
Design Arena: UI components10451102R1 0528
Design Arena: game dev10791098R1 0528
Design Arena: data viz10981182R1 0528
Design Arena: 3D10821111R1 0528
Design Arena: all code categories11171139R1 0528
Design Arena: SVG10161038R1 0528
Design Arena: ASCII art1041Not measuredOnly Trinity Large Thinking measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index118
General benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
IFBench56.3%39.6%Trinity Large Thinking
Long context reasoning (AA-LCR)38.0%55.7%R1 0528
Fiction.LiveBenchNot measured75.0%Only R1 0528 measured
Creative writing (Lech Mazur)Not measured81.9%Only R1 0528 measured
Surface Evolver Bench15.6%Not measuredOnly Trinity Large Thinking measured
LMArena Text13401428R1 0528
LMArena Text: instruction following13261382R1 0528
LMArena Text: creative writing13081405R1 0528
LMArena Text: English13561437R1 0528
LMArena Text: non-English13251412R1 0528
LMArena Text: Chinese13711442R1 0528
LMArena Text: German13561404R1 0528
LMArena Text: Japanese13121391R1 0528
LMArena Text: Korean13061360R1 0528
LMArena Text: French13661417R1 0528
LMArena Text: Spanish13271411R1 0528
LMArena Text: Russian13381423R1 0528
LMArena Text: Polish13121428R1 0528
LMArena Text: multi-turn13201405R1 0528
LMArena Text: longer queries13181391R1 0528
LMArena Text: writing and language13171402R1 0528
LMArena Text: entertainment and media12961400R1 0528
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Trinity Large Thinking and R1 0528
BenchmarkTrinity Large ThinkingR1 0528Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Trinity Large Thinking$0.0006Fits in one request
R1 0528$0.0016Fits in one request

Trinity Large Thinking costs less

Repository review

50K input + 3K output tokens

Trinity Large Thinking$0.015Fits in one request
R1 0528$0.031Fits in one request

Trinity Large Thinking costs less

Agent loop

200K input + 10K output tokens

Trinity Large Thinking$0.058Fits in one request
R1 0528$0.121Exceeds the context window

Trinity Large Thinking costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Trinity Large Thinking and R1 0528
SpecificationArcee AI Trinity Large ThinkingDeepSeek R1 0528
MakerArcee AIDeepSeek
WeightsOpen weightsOpen weights
ReleasedApril 1, 2026May 28, 2025
Context window262K164K
Input $/Mtok$0.25$0.50
Output $/Mtok$0.80$2.15
Coding index5.471.4
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Trinity Large Thinking better than R1 0528 for coding?

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 5.4 for Trinity Large Thinking. Pick Trinity Large Thinking when output tokens cost 2.7x less, or when the context window is larger, 262K against 164K tokens.

Which is cheaper, Trinity Large Thinking or R1 0528?

Trinity Large Thinking costs $0.25 per million input tokens and $0.80 per million output tokens; R1 0528 costs $0.50 and $2.15. Cost per solved task is known for neither of them.

Which has the bigger context window, Trinity Large Thinking or R1 0528?

Trinity Large Thinking, with 262K tokens against 164K.

How many benchmarks is the Trinity Large Thinking vs R1 0528 comparison based on?

42 benchmarks have a result for both models as of October 21, 2026. Trinity Large Thinking's coding index rests on 1 independent benchmark and R1 0528's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next