Noometry

Model comparison

Claude 3 Sonnet vs Granite 3.0 8b Instruct

Granite 3.0 8b Instruct is the stronger model overall, scoring 31.6 to 29.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Granite 3.0 8b Instruct IBM

31.6

Rank #270 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Claude 3 Sonnet scores higher in 4 categories and Granite 3.0 8b Instruct in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Granite 3.0 8b Instruct leads 32.8 to 10.7.
  • The biggest single-benchmark swing is BigCodeBench Complete: 53.8% for Claude 3 Sonnet and 35.4% for Granite 3.0 8b Instruct.
  • Granite 3.0 8b Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGranite 3.0 8b Instruct
ProviderAnthropicIBM
Noometry Index29.031.6
Released2024-02-29—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3014

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

Category by category

Coding Too close to call

Claude 3 Sonnet: 29.6 (#302), Granite 3.0 8b Instruct: 29.7 (#301)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
BigCodeBench Instruct42.7%29.3%
LMArena Coding12231112
BigCodeBench Complete53.8%35.4%
WeirdML10.2%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Too close to call

Claude 3 Sonnet: 20.5 (#237), Granite 3.0 8b Instruct: 20.9 (#230)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Hard Prompts11971092
DTBench53.6%—
Epoch Capabilities Index120.7—
WinoGrande75.1%—

Math Granite 3.0 8b Instruct leads

Claude 3 Sonnet: 10.7 (#310), Granite 3.0 8b Instruct: 32.8 (#210)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Math12131143
OTIS Mock AIME 2024-20252.5%—
MATH Level 518.2%—

Knowledge Granite 3.0 8b Instruct leads

Claude 3 Sonnet: 21.1 (#276), Granite 3.0 8b Instruct: 29.6 (#236)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Expert11731087
GPQA Diamond40.6%—
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Granite 3.0 8b Instruct: —

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Vision984—

Multilingual Claude 3 Sonnet leads

Claude 3 Sonnet: 37.8 (#234), Granite 3.0 8b Instruct: 27.2 (#276)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Non-English12051037
LMArena Chinese11891063
LMArena Russian12271060
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Spanish1204—

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Granite 3.0 8b Instruct: 56.0 (#276)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Instruction Following11991088

Long Context Claude 3 Sonnet leads

Claude 3 Sonnet: 36.7 (#228), Granite 3.0 8b Instruct: 34.0 (#252)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Longer Query12111122

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.1 (#238), Granite 3.0 8b Instruct: 31.1 (#285)

BenchmarkClaude 3 SonnetGranite 3.0 8b Instruct
LMArena Text12181096
LMArena Creative Writing11861071
LMArena Multi-Turn12271063

Frequently asked questions

Is Claude 3 Sonnet better than Granite 3.0 8b Instruct?

Granite 3.0 8b Instruct is the stronger model overall, scoring 31.6 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Granite 3.0 8b Instruct better for coding?

They score almost the same on coding (29.6 vs 29.7); test both on your own repository before choosing.

How many benchmarks do Claude 3 Sonnet and Granite 3.0 8b Instruct share?

14 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Granite 3.0 8b Instruct has 14.

Related comparisons

Go deeper