LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Trinity Large Thinking vs GPT-5.3-Codex

Updated October 21, 2026. 18 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 GPT-5.3-Codex
Trinity Large ThinkingArcee AI
Coding
5.4
Overall
10.8
Output $/M
$0.80
2
GPT-5.3-CodexOpenAI
Coding
29.5
Overall
32.5
Output $/M
$14.00
16
vs boards won of 18 shared

Decision reading

Pick GPT-5.3-Codex for coding: it scores 29.5 on the Vibe Coding Index against 5.4 for Trinity Large Thinking.

Pick Trinity Large Thinking when output tokens cost 17.5x less, or when what matters is τ²-Bench Telecom or Design Arena: 3D, where it leads.

Model ATrinity Large ThinkingArcee AI5.4/1001 independent benchmarkNo cost per solved taskModel BGPT-5.3-CodexOpenAI29.5/1001 independent benchmark$0.59 per solved task
Shared results
18
Trinity Large Thinking only
34
GPT-5.3-Codex only
16
Like-for-like categories
6 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, GPT-5.3-Codex 29.5 from 1 benchmark.
Widest category
General, 32.2 points apart on average over 2 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): Trinity Large Thinking 38.0% against GPT-5.3-Codex 83.3%, 45.3 points apart on a 0 to 100 scale.
Output price
Trinity Large Thinking $0.80 against GPT-5.3-Codex $14.00 per million output tokens, 17.5x apart.
Context window
Trinity Large Thinking takes 262K tokens, GPT-5.3-Codex 400K.

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 ThinkingBarsGPT-5.3-CodexTies
Coding04
Intelligence01
Agentic work10
Reasoning02
Web design17
General02
All shared boards216
CodingLike-for-likeFour of these boards feed the Vibe Coding Index04
Coding benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
LMArena WebDev12381407GPT-5.3-Codex
AA Coding Index25.8Not measuredOnly Trinity Large Thinking measured
LiveCodeBench (Vals AI)Not measured87.3%Only GPT-5.3-Codex measured
SWE-bench Verified (Vals AI)Not measured78.0%Only GPT-5.3-Codex measured
Vibe Code Bench (Vals AI)Not measured61.8%Only GPT-5.3-Codex measured
IOI (Vals AI)Not measured53.8%Only GPT-5.3-Codex measured
SciCode40.6%Not measuredOnly Trinity Large Thinking measured
Terminal-Bench Hard (Artificial Analysis run)22.7%53.0%GPT-5.3-Codex
Terminal-BenchNot measured78.4%Only GPT-5.3-Codex measured
WeirdMLNot measured79.3%Only GPT-5.3-Codex measured
ALE-BenchNot measured1655.2Only GPT-5.3-Codex measured
LMArena Text: coding1357Not measuredOnly Trinity Large Thinking measured
LMArena Text: software and IT1362Not measuredOnly Trinity Large Thinking measured
LMArena WebDev: React12311395GPT-5.3-Codex
LMArena WebDev: HTML12401422GPT-5.3-Codex
LMArena WebDev: from an imageNot measured1443Only GPT-5.3-Codex measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
AA Intelligence Index10.832.5GPT-5.3-Codex
Epoch Capabilities IndexNot measured157.1Only GPT-5.3-Codex measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
AA Agentic Index1.0Not measuredOnly Trinity Large Thinking measured
Design Arena: agents building web appsNot measured1033Only GPT-5.3-Codex measured
Design Arena: agents building full-stack appsNot measured983Only GPT-5.3-Codex measured
Design Arena: agents building mobile appsNot measured1054Only GPT-5.3-Codex measured
Design Arena: agents building Android appsNot measured1084Only GPT-5.3-Codex measured
Design Arena: agents building Godot gamesNot measured1124Only GPT-5.3-Codex measured
τ²-Bench Telecom90.1%86.0%Trinity Large Thinking
METR time horizonsNot measured74.5%Only GPT-5.3-Codex measured
Vending-Bench 2Not measured$5,940Only GPT-5.3-Codex measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
Reasoning benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
GPQA Diamond (Artificial Analysis run)75.2%91.5%GPT-5.3-Codex
Humanity's Last Exam (Artificial Analysis run)15.8%42.5%GPT-5.3-Codex
LMArena Text: hard prompts1342Not measuredOnly Trinity Large Thinking measured
LMArena Text: expert1359Not measuredOnly Trinity Large Thinking measured
LMArena Text: hard prompts in English1356Not measuredOnly Trinity Large Thinking measured
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Math benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
LMArena Text: math1365Not measuredOnly Trinity Large Thinking measured
LMArena Text: mathematical work1350Not measuredOnly Trinity Large Thinking measured
Neither model has a result on the other 11 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Knowledge benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
CaseLaw (Vals AI)57.9%Not measuredOnly Trinity Large Thinking measured
CorpFin (Vals AI)54.7%Not measuredOnly Trinity Large Thinking measured
LMArena Text: science1355Not measuredOnly Trinity Large Thinking measured
LMArena Text: medicine and healthcare1349Not measuredOnly Trinity Large Thinking measured
LMArena Text: legal and government1345Not measuredOnly Trinity Large Thinking measured
LMArena Text: business and finance1329Not measuredOnly Trinity Large Thinking measured
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
Design Arena: websites11371163GPT-5.3-Codex
Design Arena: UI components10451137GPT-5.3-Codex
Design Arena: game dev10791162GPT-5.3-Codex
Design Arena: data viz10981164GPT-5.3-Codex
Design Arena: 3D10821008Trinity Large Thinking
Design Arena: all code categories11171145GPT-5.3-Codex
Design Arena: SVG10161129GPT-5.3-Codex
Design Arena: ASCII art10411151GPT-5.3-Codex
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for Trinity Large Thinking and GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
IFBench56.3%75.4%GPT-5.3-Codex
Long context reasoning (AA-LCR)38.0%83.3%GPT-5.3-Codex
Surface Evolver Bench15.6%Not measuredOnly Trinity Large Thinking measured
LMArena Text1340Not measuredOnly Trinity Large Thinking measured
LMArena Text: instruction following1326Not measuredOnly Trinity Large Thinking measured
LMArena Text: creative writing1308Not measuredOnly Trinity Large Thinking measured
LMArena Text: English1356Not measuredOnly Trinity Large Thinking measured
LMArena Text: non-English1325Not measuredOnly Trinity Large Thinking measured
LMArena Text: Chinese1371Not measuredOnly Trinity Large Thinking measured
LMArena Text: German1356Not measuredOnly Trinity Large Thinking measured
LMArena Text: Japanese1312Not measuredOnly Trinity Large Thinking measured
LMArena Text: Korean1306Not measuredOnly Trinity Large Thinking measured
LMArena Text: French1366Not measuredOnly Trinity Large Thinking measured
LMArena Text: Spanish1327Not measuredOnly Trinity Large Thinking measured
LMArena Text: Russian1338Not measuredOnly Trinity Large Thinking measured
LMArena Text: Polish1312Not measuredOnly Trinity Large Thinking measured
LMArena Text: multi-turn1320Not measuredOnly Trinity Large Thinking measured
LMArena Text: longer queries1318Not measuredOnly Trinity Large Thinking measured
LMArena Text: writing and language1317Not measuredOnly Trinity Large Thinking measured
LMArena Text: entertainment and media1296Not measuredOnly Trinity Large Thinking measured
Neither model has a result on the other 26 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 GPT-5.3-Codex
BenchmarkTrinity Large ThinkingGPT-5.3-CodexLeader
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
GPT-5.3-Codex$0.0088Fits in one request

Trinity Large Thinking costs less

Repository review

50K input + 3K output tokens

Trinity Large Thinking$0.015Fits in one request
GPT-5.3-Codex$0.130Fits in one request

Trinity Large Thinking costs less

Agent loop

200K input + 10K output tokens

Trinity Large Thinking$0.058Fits in one request
GPT-5.3-Codex$0.490Fits in one request

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 GPT-5.3-Codex
SpecificationArcee AI Trinity Large ThinkingOpenAI GPT-5.3-Codex
MakerArcee AIOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 1, 2026February 24, 2026
Context window262K400K
Input $/Mtok$0.25$1.75
Output $/Mtok$0.80$14.00
Coding index5.429.5
Independent measurements behind it11
Cost per solved taskNot computable$0.59
SourceOpenRouter listingOpenRouter listing

Questions

Is Trinity Large Thinking better than GPT-5.3-Codex for coding?

Pick GPT-5.3-Codex for coding: it scores 29.5 on the Vibe Coding Index against 5.4 for Trinity Large Thinking. Pick Trinity Large Thinking when output tokens cost 17.5x less, or when what matters is τ²-Bench Telecom or Design Arena: 3D, where it leads.

Which is cheaper, Trinity Large Thinking or GPT-5.3-Codex?

Trinity Large Thinking costs $0.25 per million input tokens and $0.80 per million output tokens; GPT-5.3-Codex costs $1.75 and $14.00. Cost per solved task is known for GPT-5.3-Codex only.

Which has the bigger context window, Trinity Large Thinking or GPT-5.3-Codex?

GPT-5.3-Codex, with 400K tokens against 262K.

How many benchmarks is the Trinity Large Thinking vs GPT-5.3-Codex comparison based on?

18 benchmarks have a result for both models as of October 21, 2026. Trinity Large Thinking's coding index rests on 1 independent benchmark and GPT-5.3-Codex's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next