Noometry

Model comparison

Granite 3.0 2b Instruct vs Qwen2.5 7B Instruct

Granite 3.0 2b Instruct is the stronger model overall, scoring 30.2 to 28.6 on the Noometry Index.

Last verified . 1 shared benchmarks.

Granite 3.0 2b Instruct IBM

30.2

Rank #284 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

28.6

Rank #314 Confirmed

Summary

  • They share 1 benchmark with published results for both. Granite 3.0 2b Instruct scores higher in 3 categories and Qwen2.5 7B Instruct in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 29.8.
  • The biggest single-benchmark swing is BigCodeBench Instruct: 20.5% for Granite 3.0 2b Instruct and 37.6% for Qwen2.5 7B Instruct.

Side by side

Granite 3.0 2b InstructQwen2.5 7B Instruct
ProviderIBMAlibaba (Qwen)
Noometry Index30.228.6
Released—2024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.17
Output $ / M tokens—$0.70
Results tracked1315

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

Category by category

Coding Qwen2.5 7B Instruct leads

Granite 3.0 2b Instruct: 27.8 (#311), Qwen2.5 7B Instruct: 35.9 (#204)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
BigCodeBench Instruct20.5%37.6%
LMArena Coding1090—
BigCodeBench Complete—46.1%

Agentic & Tool Use Not comparable

Granite 3.0 2b Instruct: —, Qwen2.5 7B Instruct: 23.5 (#117)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
BALROG—7.8%

Reasoning Granite 3.0 2b Instruct leads

Granite 3.0 2b Instruct: 19.6 (#234), Qwen2.5 7B Instruct: 14.3 (#317)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
Chess Puzzles—0%
LMArena Hard Prompts1073—
DTBench—47.7%
LMCA—6.4%
Epoch Capabilities Index—118.44

Math Granite 3.0 2b Instruct leads

Granite 3.0 2b Instruct: 29.7 (#215), Qwen2.5 7B Instruct: 11.8 (#300)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
OTIS Mock AIME 2024-2025—2.5%
Omni-MATH—29.4%
LMArena Math1117—

Knowledge Granite 3.0 2b Instruct leads

Granite 3.0 2b Instruct: 28.4 (#238), Qwen2.5 7B Instruct: 17.0 (#281)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
GPQA Diamond—35.5%
MMLU-Pro—53.9%
GPQA (HELM)—34.1%
LMArena Expert1064—
MMLU—72.9%

Multilingual Not comparable

Granite 3.0 2b Instruct: 27.1 (#273), Qwen2.5 7B Instruct: —

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
LMArena Non-English1033—
LMArena Chinese1070—
LMArena Russian1045—

Instruction Following Qwen2.5 7B Instruct leads

Granite 3.0 2b Instruct: 54.2 (#279), Qwen2.5 7B Instruct: 63.4 (#226)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
IFEval—74.1%
LMArena Instruction Following1056—

Long Context Not comparable

Granite 3.0 2b Instruct: 32.5 (#263), Qwen2.5 7B Instruct: —

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
LMArena Longer Query1071—

Writing & Preference Qwen2.5 7B Instruct leads

Granite 3.0 2b Instruct: 29.8 (#287), Qwen2.5 7B Instruct: 48.8 (#194)

BenchmarkGranite 3.0 2b InstructQwen2.5 7B Instruct
LMArena Text1080—
LMArena Creative Writing1046—
WildBench—73.1%
LMArena Multi-Turn1053—

Frequently asked questions

Is Granite 3.0 2b Instruct better than Qwen2.5 7B Instruct?

Granite 3.0 2b Instruct is the stronger model overall, scoring 30.2 to 28.6 on the Noometry Index.

Is Granite 3.0 2b Instruct or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 27.8 in the Noometry coding category.

How many benchmarks do Granite 3.0 2b Instruct and Qwen2.5 7B Instruct share?

1 benchmark has published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper