Noometry

Model comparison

DeepSeek LLM 67B vs Trinity Large Thinking

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 24.9 on the Noometry Index.

Last verified . 10 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Trinity Large Thinking Arcee AI

38.6

Rank #185 Confirmed

Summary

  • They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 7.0.

Side by side

DeepSeek LLM 67BTrinity Large Thinking
ProviderDeepSeekArcee AI
Noometry Index24.938.6
Released2023-11-292026-04-01
WeightsOpenOpen
Context window—262K
Max output—80K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.80
Results tracked1524

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

Category by category

Coding Trinity Large Thinking leads

DeepSeek LLM 67B: 31.9 (#278), Trinity Large Thinking: 34.1 (#244)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Coding10961381
LMArena WebDev—1238
SciCode—36.1%

Reasoning Too close to call

DeepSeek LLM 67B: 16.5 (#304), Trinity Large Thinking: 16.9 (#298)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Hard Prompts10701350
NYT Connections (extended)—16.5%
CritPt—0.9%
Chess Puzzles0%—
Thematic Generalization—41.6%
Surface Evolver Bench—15.6%
Epoch Capabilities Index110.5—

Math Trinity Large Thinking leads

DeepSeek LLM 67B: 8.7 (#324), Trinity Large Thinking: 37.6 (#149)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Math11081366
OTIS Mock AIME 2024-20250.8%—
MATH Level 56.4%—

Knowledge Trinity Large Thinking leads

DeepSeek LLM 67B: 7.0 (#313), Trinity Large Thinking: 40.9 (#113)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
GPQA Diamond24.6%—
Vectara Hallucination Rate—6.9%
LMArena Expert—1360

Multilingual Trinity Large Thinking leads

DeepSeek LLM 67B: 29.4 (#267), Trinity Large Thinking: 46.2 (#160)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Non-English10731325
LMArena Chinese11321373
LMArena French—1374
LMArena German—1356
LMArena Japanese—1311
LMArena Korean—1306
LMArena Russian—1337
LMArena Spanish—1357

Instruction Following Trinity Large Thinking leads

DeepSeek LLM 67B: 55.4 (#277), Trinity Large Thinking: 70.5 (#162)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Instruction Following10791334

Long Context Trinity Large Thinking leads

DeepSeek LLM 67B: 33.1 (#265), Trinity Large Thinking: 41.3 (#144)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Longer Query10921355

Writing & Preference Trinity Large Thinking leads

DeepSeek LLM 67B: 31.6 (#282), Trinity Large Thinking: 53.8 (#158)

BenchmarkDeepSeek LLM 67BTrinity Large Thinking
LMArena Text11051340
LMArena Creative Writing10671320
LMArena Multi-Turn10821342

Frequently asked questions

Is DeepSeek LLM 67B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Trinity Large Thinking share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Trinity Large Thinking has 24.

Related comparisons

Go deeper