Noometry

Model comparison

DeepSeek-V3.1 vs Trinity Large Thinking

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Trinity Large Thinking Arcee AI

38.1

Rank #180 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Trinity Large Thinking in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.3 to 16.3.
  • Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
  • Trinity Large Thinking accepts more context: 262K tokens versus 164K.

Side by side

DeepSeek-V3.1Trinity Large Thinking
ProviderDeepSeekArcee AI
Noometry Index42.238.1
Released2025-08-212026-04-01
WeightsOpenOpen
Context window164K262K
Max output8K80K
Input $ / M tokens$0.25$0.25
Output $ / M tokens$0.95$0.80
Results tracked2724

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 39.8 (#140), Trinity Large Thinking: 33.8 (#238)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Coding14171381
LMArena WebDev—1238
SciCode—36.1%
WeirdML38.4%—

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), Trinity Large Thinking: 16.3 (#298)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Hard Prompts14171350
SimpleBench40%—
Kagi LLM Benchmark53.2%—
NYT Connections (extended)—16.5%
CritPt—0.9%
Thematic Generalization—41.6%
DTBench82.7%—
LMCA24.3%—
Surface Evolver Bench—15.6%
Epoch Capabilities Index139.92—
ForecastBench58—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), Trinity Large Thinking: 34.9 (#149)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Math14201366

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), Trinity Large Thinking: 40.3 (#107)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
Vectara Hallucination Rate5.5%6.9%
LMArena Expert14031359

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.8 (#100), Trinity Large Thinking: 46.4 (#155)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Non-English14001325
LMArena Chinese14701372
LMArena French14471374
LMArena German14121356
LMArena Japanese13741312
LMArena Korean13371304
LMArena Russian14051338
LMArena Spanish14291356

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 74.1 (#105), Trinity Large Thinking: 70.7 (#157)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Instruction Following14001334

Long Context Trinity Large Thinking leads

DeepSeek-V3.1: 36.3 (#227), Trinity Large Thinking: 41.2 (#139)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Longer Query14221355
Fiction.LiveBench52.8%—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), Trinity Large Thinking: 54.0 (#152)

BenchmarkDeepSeek-V3.1Trinity Large Thinking
LMArena Text14201340
LMArena Creative Writing14011321
LMArena Multi-Turn14081342
EQ-Bench Creative Writing1436—

Frequently asked questions

Is DeepSeek-V3.1 better than Trinity Large Thinking?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 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; DeepSeek-V3.1 lists at $0.25 and $0.95.

Is DeepSeek-V3.1 or Trinity Large Thinking better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do DeepSeek-V3.1 and Trinity Large Thinking share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Trinity Large Thinking has 24.

Related comparisons

Go deeper