Noometry

Model comparison

Claude 3 Haiku vs Granite 3.1 2b Instruct

Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 25.7 on the Noometry Index.

Last verified . 12 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Granite 3.1 2b Instruct IBM

32.6

Rank #243 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Claude 3 Haiku scores higher in 3 categories and Granite 3.1 2b Instruct in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Granite 3.1 2b Instruct leads 30.6 to 9.2.
  • Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuGranite 3.1 2b Instruct
ProviderAnthropicIBM
Noometry Index25.732.6
Released2024-03-07—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3712

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

Category by category

Coding Granite 3.1 2b Instruct leads

Claude 3 Haiku: 26.1 (#320), Granite 3.1 2b Instruct: 32.9 (#255)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Coding11991149
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Granite 3.1 2b Instruct leads

Claude 3 Haiku: 15.7 (#303), Granite 3.1 2b Instruct: 21.0 (#206)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Hard Prompts11741138
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.3—
ForecastBench53.2—
WinoGrande74.2%—

Math Granite 3.1 2b Instruct leads

Claude 3 Haiku: 9.2 (#313), Granite 3.1 2b Instruct: 30.6 (#206)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Math11881159
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Granite 3.1 2b Instruct leads

Claude 3 Haiku: 17.3 (#280), Granite 3.1 2b Instruct: 30.3 (#223)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Expert11481131
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Granite 3.1 2b Instruct: —

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#238), Granite 3.1 2b Instruct: 29.2 (#264)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Non-English11781068
LMArena Chinese11551138
LMArena Russian12041063
LMArena French1194—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1108—
LMArena Spanish1165—

Instruction Following Claude 3 Haiku leads

Claude 3 Haiku: 61.5 (#242), Granite 3.1 2b Instruct: 58.0 (#259)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Instruction Following11741116

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#232), Granite 3.1 2b Instruct: 35.0 (#239)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Longer Query11911155

Writing & Preference Granite 3.1 2b Instruct leads

Claude 3 Haiku: 29.8 (#286), Granite 3.1 2b Instruct: 34.3 (#269)

BenchmarkClaude 3 HaikuGranite 3.1 2b Instruct
LMArena Text11951127
LMArena Creative Writing11571116
LMArena Multi-Turn11901099
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Granite 3.1 2b Instruct?

Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or Granite 3.1 2b Instruct better for coding?

Granite 3.1 2b Instruct scores higher on coding benchmarks: 32.9 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Granite 3.1 2b Instruct share?

12 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Granite 3.1 2b Instruct has 12.

Related comparisons

Go deeper