Noometry

Model comparison

GPT-4 Turbo vs Trinity Large Thinking

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Trinity Large Thinking Arcee AI

38.6

Rank #185 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Trinity Large Thinking leads 37.6 to 9.0.
  • Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Trinity Large Thinking accepts more context: 262K tokens versus 128K.
  • Trinity Large Thinking has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboTrinity Large Thinking
ProviderOpenAIArcee AI
Noometry Index30.538.6
Released2023-11-062026-04-01
WeightsProprietaryOpen
Context window128K262K
Max output4K80K
Input $ / M tokens$10$0.25
Output $ / M tokens$30$0.80
Results tracked3624

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

GPT-4 Turbo: 33.8 (#249), Trinity Large Thinking: 34.1 (#244)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Coding12681381
LMArena WebDev—1238
SciCode—36.1%
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Trinity Large Thinking: —

BenchmarkGPT-4 TurboTrinity Large Thinking
METR Time Horizons36.7%—

Reasoning Trinity Large Thinking leads

GPT-4 Turbo: 15.3 (#317), Trinity Large Thinking: 16.9 (#298)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Hard Prompts12511350
SimpleBench25.1%—
NYT Connections (extended)—16.5%
CritPt—0.9%
Chess Puzzles6%—
Thematic Generalization—41.6%
DTBench61.6%—
LMCA9.8%—
Surface Evolver Bench—15.6%
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Trinity Large Thinking leads

GPT-4 Turbo: 9.0 (#322), Trinity Large Thinking: 37.6 (#149)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Math12721366
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge Trinity Large Thinking leads

GPT-4 Turbo: 24.3 (#268), Trinity Large Thinking: 40.9 (#113)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Expert12231360
GPQA Diamond46.6%—
Confabulations28.4%—
Vectara Hallucination Rate—6.9%
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Trinity Large Thinking: —

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Vision1090—

Multilingual Trinity Large Thinking leads

GPT-4 Turbo: 40.5 (#216), Trinity Large Thinking: 46.2 (#160)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Non-English12451325
LMArena Chinese12421373
LMArena French12761374
LMArena German12591356
LMArena Japanese11941311
LMArena Korean11871306
LMArena Russian12591337
LMArena Spanish12601357

Instruction Following Trinity Large Thinking leads

GPT-4 Turbo: 65.8 (#216), Trinity Large Thinking: 70.5 (#162)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Instruction Following12491334

Long Context Trinity Large Thinking leads

GPT-4 Turbo: 38.0 (#206), Trinity Large Thinking: 41.3 (#144)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Longer Query12541355

Writing & Preference Trinity Large Thinking leads

GPT-4 Turbo: 47.7 (#206), Trinity Large Thinking: 53.8 (#158)

BenchmarkGPT-4 TurboTrinity Large Thinking
LMArena Text12721340
LMArena Creative Writing12691320
LMArena Multi-Turn12671342

Frequently asked questions

Is GPT-4 Turbo better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or Trinity Large Thinking?

Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Trinity Large Thinking better for coding?

They score almost the same on coding (33.8 vs 34.1); test both on your own repository before choosing.

Which has the bigger context window?

Trinity Large Thinking does, with 262K tokens against 128K.

How many benchmarks do GPT-4 Turbo and Trinity Large Thinking share?

17 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Trinity Large Thinking has 24.

Related comparisons

Go deeper