Noometry

Model comparison

Claude 3 Haiku vs Granite 3.0 2b Instruct

Granite 3.0 2b Instruct is the stronger model overall, scoring 30.2 to 25.7 on the Noometry Index.

Last verified . 13 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Granite 3.0 2b Instruct IBM

30.2

Rank #284 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Granite 3.0 2b Instruct in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Granite 3.0 2b Instruct leads 29.7 to 9.2.
  • The biggest single-benchmark swing is BigCodeBench Instruct: 39.4% for Claude 3 Haiku and 20.5% for Granite 3.0 2b Instruct.
  • Granite 3.0 2b Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuGranite 3.0 2b Instruct
ProviderAnthropicIBM
Noometry Index25.730.2
Released2024-03-07—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3713

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

Category by category

Coding Granite 3.0 2b Instruct leads

Claude 3 Haiku: 26.1 (#320), Granite 3.0 2b Instruct: 27.8 (#311)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
BigCodeBench Instruct39.4%20.5%
LMArena Coding11991090
WeirdML9.8%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Granite 3.0 2b Instruct leads

Claude 3 Haiku: 15.7 (#303), Granite 3.0 2b Instruct: 19.6 (#234)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Hard Prompts11741073
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.3—
ForecastBench53.2—
WinoGrande74.2%—

Math Granite 3.0 2b Instruct leads

Claude 3 Haiku: 9.2 (#313), Granite 3.0 2b Instruct: 29.7 (#215)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Math11881117
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Granite 3.0 2b Instruct leads

Claude 3 Haiku: 17.3 (#280), Granite 3.0 2b Instruct: 28.4 (#238)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Expert11481064
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Granite 3.0 2b Instruct: —

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#238), Granite 3.0 2b Instruct: 27.1 (#273)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Non-English11781033
LMArena Chinese11551070
LMArena Russian12041045
LMArena French1194—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1108—
LMArena Spanish1165—

Instruction Following Claude 3 Haiku leads

Claude 3 Haiku: 61.5 (#242), Granite 3.0 2b Instruct: 54.2 (#279)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Instruction Following11741056

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#232), Granite 3.0 2b Instruct: 32.5 (#263)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Longer Query11911071

Writing & Preference Too close to call

Claude 3 Haiku: 29.8 (#286), Granite 3.0 2b Instruct: 29.8 (#287)

BenchmarkClaude 3 HaikuGranite 3.0 2b Instruct
LMArena Text11951080
LMArena Creative Writing11571046
LMArena Multi-Turn11901053
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Granite 3.0 2b Instruct?

Granite 3.0 2b Instruct is the stronger model overall, scoring 30.2 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or Granite 3.0 2b Instruct better for coding?

Granite 3.0 2b Instruct scores higher on coding benchmarks: 27.8 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Granite 3.0 2b Instruct share?

13 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Granite 3.0 2b Instruct has 13.

Related comparisons

Go deeper