Noometry

Model comparison

DeepSeek V4.1 Flash vs Trinity Large Thinking

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 38.6 on the Noometry Index.

Last verified . 22 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Trinity Large Thinking Arcee AI

38.6

Rank #185 Confirmed

Summary

  • They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 16.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 16.5% for Trinity Large Thinking.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.

Side by side

DeepSeek V4.1 FlashTrinity Large Thinking
ProviderDeepSeekArcee AI
Noometry Index52.838.6
Released2026-09-092026-04-01
WeightsOpenOpen
Context window1M262K
Max output393K80K
Input $ / M tokens$0.15$0.25
Output $ / M tokens$0.60$0.80
Results tracked3724

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Trinity Large Thinking: 34.1 (#244)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena WebDev16191238
SciCode51.9%36.1%
LMArena Coding15061381
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Trinity Large Thinking: —

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Trinity Large Thinking: 16.9 (#298)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
NYT Connections (extended)89.6%16.5%
CritPt14.3%0.9%
LMArena Hard Prompts14831350
Surface Evolver Bench46.3%15.6%
Thematic Generalization—41.6%
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Trinity Large Thinking: 37.6 (#149)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Math14771366
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Trinity Large Thinking: 40.9 (#113)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Expert15061360
GPQA Diamond89.8%—
Vectara Hallucination Rate—6.9%

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Trinity Large Thinking: —

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Trinity Large Thinking: 46.2 (#160)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Non-English14481325
LMArena Chinese14971373
LMArena French14521374
LMArena German14841356
LMArena Japanese14121311
LMArena Korean14521306
LMArena Russian14711337
LMArena Spanish14591357

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Trinity Large Thinking: 70.5 (#162)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Instruction Following14741334

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Trinity Large Thinking: 41.3 (#144)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Longer Query14751355

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Trinity Large Thinking: 53.8 (#158)

BenchmarkDeepSeek V4.1 FlashTrinity Large Thinking
LMArena Text14621340
LMArena Creative Writing14351320
LMArena Multi-Turn14571342
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Trinity Large Thinking?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 38.6 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Trinity Large Thinking?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.

Is DeepSeek V4.1 Flash or Trinity Large Thinking better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 262K.

How many benchmarks do DeepSeek V4.1 Flash and Trinity Large Thinking share?

22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Trinity Large Thinking has 24.

Related comparisons

Go deeper