Noometry

Model comparison

Claude 3 Haiku vs Trinity Large Thinking

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 25.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Trinity Large Thinking Arcee AI

38.6

Rank #185 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Haiku 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 9.8.
  • Trinity Large Thinking has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuTrinity Large Thinking
ProviderAnthropicArcee AI
Noometry Index25.938.6
Released2024-03-072026-04-01
WeightsProprietaryOpen
Context window—262K
Max output—80K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.80
Results tracked3724

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

Category by category

Coding Trinity Large Thinking leads

Claude 3 Haiku: 26.4 (#325), Trinity Large Thinking: 34.1 (#244)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Coding11991381
LMArena WebDev—1238
SciCode—36.1%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Too close to call

Claude 3 Haiku: 16.3 (#307), Trinity Large Thinking: 16.9 (#298)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Hard Prompts11741350
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—16.5%
CritPt—0.9%
Thematic Generalization—41.6%
DTBench50.1%—
LMCA8.8%—
Surface Evolver Bench—15.6%
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math Trinity Large Thinking leads

Claude 3 Haiku: 9.8 (#319), Trinity Large Thinking: 37.6 (#149)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Math11881366
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Trinity Large Thinking leads

Claude 3 Haiku: 17.3 (#285), Trinity Large Thinking: 40.9 (#113)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Expert11481360
GPQA Diamond36.3%—
Confabulations34.2%—
Vectara Hallucination Rate—6.9%
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Trinity Large Thinking: —

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Vision950—
ScienceQA72%—

Multilingual Trinity Large Thinking leads

Claude 3 Haiku: 36.0 (#243), Trinity Large Thinking: 46.2 (#160)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Non-English11781325
LMArena Chinese11551373
LMArena French11951374
LMArena German11741356
LMArena Japanese11021311
LMArena Korean11091306
LMArena Russian12041337
LMArena Spanish11661357

Instruction Following Trinity Large Thinking leads

Claude 3 Haiku: 61.3 (#247), Trinity Large Thinking: 70.5 (#162)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Instruction Following11731334

Long Context Trinity Large Thinking leads

Claude 3 Haiku: 36.1 (#237), Trinity Large Thinking: 41.3 (#144)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Longer Query11901355

Writing & Preference Trinity Large Thinking leads

Claude 3 Haiku: 29.7 (#291), Trinity Large Thinking: 53.8 (#158)

BenchmarkClaude 3 HaikuTrinity Large Thinking
LMArena Text11951340
LMArena Creative Writing11571320
LMArena Multi-Turn11901342
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Trinity Large Thinking share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Trinity Large Thinking has 24.

Related comparisons

Go deeper